{"as_of":"2026-08-11T15:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3a32d26d6f0f348512340fece3072c638c4cd7053ac87183ec9422bc39b2b724","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:48:57.619008Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.14999/citation-record","integrity":"/paper/2501.14999/integrity","json":"/paper/2501.14999/citation-record.json","paper":"/paper/2501.14999"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:48:58.679863Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"5d25ca23-b166-4ac3-aa4f-cd6e365b27de","year":2016},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.328886Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:f1510d0e68360c99f9b0d06100e8b4f1de3626cef8c77b6eb6cb4bce389b59e9","observation_id":"ce74e9e5-f2a1-4034-b3ed-e4c54069281a","resolution":{"observed_at":"2026-08-10T14:48:58.684545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.663570Z","title":"Towards practical certifiable patch defense with vision transformer,","venue":null,"work_id":"b561ea6a-0132-4e06-a17d-23104c5ef510","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.334819Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:6f2e9169173b5dea09664eb82ed9861c113a497bde56449e9355758e8dc25ff8","observation_id":"e92dbc40-34a6-47f9-89e4-82ebe7fe8221","resolution":{"observed_at":"2026-08-10T14:48:58.669426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.648168Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":"87d03e36-6110-4507-9dc4-4fff77fb668f","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.339454Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:b054b08cd612ec2abe4ca5e73036a965c1a721bbcd40b8f963d06cb6f85015ab","observation_id":"ad3565e6-3f26-4ca4-812e-354f2eec6c19","resolution":{"observed_at":"2026-08-10T14:48:58.653254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.631909Z","title":"Cross-shaped adversarial patch attack,","venue":null,"work_id":"1922bc10-392f-4039-872b-ca3b8a775415","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.344569Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:38e19ed7eddd0884b7d0890ff29833d0bd85f2b5c8c65b2b18d0930618843374","observation_id":"02b75289-9c15-4f44-81ba-311dcdb6192b","resolution":{"observed_at":"2026-08-10T14:48:58.637106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.614794Z","title":"Adversarial attacks on video object segmentation with hard region discovery,","venue":null,"work_id":"f62178e0-141e-427b-9448-0f393e735cf1","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.349247Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:fe01190a59101c7e1db7f0cd1d8ebcf6594c0190d75a2b9be1d909ef627ccbe8","observation_id":"9497e1c2-7da0-4476-9834-bf99c57dff8b","resolution":{"observed_at":"2026-08-10T14:48:58.620066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.597834Z","title":"Diffusion patch attack with spatial-temporal cross-evolution for video recognition,","venue":null,"work_id":"858181be-ae44-4aae-a66b-f5de34d3ad8a","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.354469Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:08fc04687b95ace4671612eebc7f0aba828d4e5e7c4559450d20ca7b96374505","observation_id":"8f0c7a96-9392-4298-ba4a-eb96fd676cc0","resolution":{"observed_at":"2026-08-10T14:48:58.603541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.582324Z","title":"Bullet-screen-emoji attack with temporal difference noise for video action recognition,","venue":null,"work_id":"c2368a69-26c0-47b6-b4f0-a83a8f0f3ada","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.359764Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:b64a952b6085712ee2c53a2bea9ad1a6e625528634f71efa41508d68d767b081","observation_id":"49e0b7d9-6488-4fcb-8679-2abf6ec3e5ac","resolution":{"observed_at":"2026-08-10T14:48:58.586453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.567207Z","title":"Only once attack: Fooling the tracker with adversarial template,","venue":null,"work_id":"6b095468-a041-4535-93bf-e19eeafb5dc1","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.364231Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:77a89597684c91a03a827383c820cd4c14bf7f25faf8ab1a5659d2a4e04fb3c5","observation_id":"8fcbc192-7b04-4a68-8beb-57b913d8517a","resolution":{"observed_at":"2026-08-10T14:48:58.572050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.552050Z","title":"A simple and strong baseline for universal targeted attacks on siamese visual tracking,","venue":null,"work_id":"c2014284-93fb-4dc9-a5de-499b6d7e6251","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.368370Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:7d454bb5a2637c35bc725f4310154ff7da4026ab30a2a985f5ecb73c713293f8","observation_id":"6c0e77df-854e-4956-aaf7-e3404bb8fd2f","resolution":{"observed_at":"2026-08-10T14:48:58.556944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.534337Z","title":"Sparse adversarial perturbations for videos,","venue":null,"work_id":"f7a4792f-0313-4d7d-a9d6-28ff0dc1052a","year":2019},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.372626Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:7b4831a8f806708c50afd07313fb2255df2befd569000cb845d489fad3b804b8","observation_id":"91544af2-f545-49ea-a4a7-452e6308deef","resolution":{"observed_at":"2026-08-10T14:48:58.539961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.517474Z","title":"The apolloscape dataset for autonomous driving,","venue":null,"work_id":"b0a730d1-c4fc-42a8-92ea-1ebbf952e19e","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.376786Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:9c3ed675962092f5d2c82f321041d5253d8b8086afa14c825c551ee821e902fd","observation_id":"f5676331-6795-4ed4-bd1b-a4906b0c525c","resolution":{"observed_at":"2026-08-10T14:48:58.522493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.500146Z","title":"A system for video surveillance and monitoring,","venue":null,"work_id":"0eadee4f-d63e-489e-bcf9-fbb353b7fa30","year":2000},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.381108Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:fea7ebb3abace8c1e3591039a77313fe47f4558f3deec5bf42432a312991d6ab","observation_id":"133fc542-7941-48ab-9e9d-8e6a566389e4","resolution":{"observed_at":"2026-08-10T14:48:58.505750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03593","last_updated":"2021-03-30T08:08:12Z","snapshot_observed_at":"2026-07-06T10:02:27.415825Z","submitted_at":"2020-10-07T18:19:09Z","title":"Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03593","snapshot_observed_at":"2026-08-10T14:48:57.385171Z","title":"Uncovering the limits of adversarial training against norm-bounded adversarial examples,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.385171Z"},"links":{"cited_paper":"/paper/2010.03593","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:3a7938991685aae7d8540f222b9220970d681d5d11a0d57fb09310852eed9ea7","observation_id":"eb968ab7-43be-4ce5-a00b-8ccd74f19c67","resolution":{"observed_at":"2026-08-10T14:48:57.385171Z","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":"2026-08-10T14:48:58.485138Z","title":"Theoretically principled trade-off between robustness and accuracy,","venue":null,"work_id":"e13164a1-688a-48b9-876f-7094437f4f4d","year":2019},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.389722Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:4609fbbcd22e7171c7b4bee78a7eda33da8860bf8670562c7b5e3f08ba57c0b6","observation_id":"5d9a704f-a082-4713-88e7-ca82318b078e","resolution":{"observed_at":"2026-08-10T14:48:58.489613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.471375Z","title":"Improving robustness using generated data,","venue":null,"work_id":"d56dcc36-917e-4cba-8156-fda3abc71dc2","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.394689Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:dd7cf3346047964a9598a1c4bcddcd2d126ca28f54daace4ea741e39747ee52f","observation_id":"830f13f9-bfd9-4db8-93cf-a71005cdc3c4","resolution":{"observed_at":"2026-08-10T14:48:58.475614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.456767Z","title":"Adversarial machine learning at scale,","venue":null,"work_id":"49adc992-9da2-45bb-ad4a-d444df7a7485","year":2016},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.398954Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:7d7123e88c306b2cc4fcd17b6dc58343ddfaf5ef785e3875a2da161aa074a7c8","observation_id":"b20b4910-9da7-400f-9a59-f7aa56c4a8cd","resolution":{"observed_at":"2026-08-10T14:48:58.461034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.441107Z","title":"Defending against multiple and unforeseen adversarial videos,","venue":null,"work_id":"afb56771-20e8-4110-9bc7-dbb9fbfe01d7","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.403381Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:9dced16aa07a26df8f4b1a336ce6176ad7ed6d2bd384fe2470f8327d3e266c5b","observation_id":"b5100662-bed8-4544-924d-54470ded858d","resolution":{"observed_at":"2026-08-10T14:48:58.446294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.424804Z","title":"Analysis and extensions of adversarial training for video classification,","venue":null,"work_id":"68931eb7-b209-4568-be24-a05f09c89923","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.408468Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:3f7beef6cc6cc92e78550df731fae2faa42eab0b82756dbb67687617ce175c3e","observation_id":"2b8edc4b-b9c8-454e-9496-137fff938037","resolution":{"observed_at":"2026-08-10T14:48:58.429767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.408196Z","title":"Defense-gan: Protecting classifiers against adversarial attacks using generative models,","venue":null,"work_id":"8675a134-bbd4-4d4a-b1bb-709c0d9ff585","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.413315Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:84143d655e342a5adc4e0812668382ad1c6338909746cffe5cb4df9316505cc3","observation_id":"488c8c5b-2a2d-4fc6-befa-8f876e16e857","resolution":{"observed_at":"2026-08-10T14:48:58.413487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.389976Z","title":"Pixelde- fend: Leveraging generative models to understand and defend against adversarial examples,","venue":null,"work_id":"ebb46751-a53e-454d-a862-24876e391e5b","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.418585Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:aa0fd1ce8ee4596c88474d048c7e0d56d1dcc59b7345f85393e75502a3f5d459","observation_id":"7a07c090-283a-4e95-8faf-3da2cfa24340","resolution":{"observed_at":"2026-08-10T14:48:58.395525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.375336Z","title":"Defending video recognition model against adversarial perturbations via defense patterns,","venue":null,"work_id":"31adfc7c-98b0-4412-8f0b-762f13bcbc68","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.423518Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:ac407b5be976199e74424936adab48e6190f1764cde7bebdc79f3758bdb61dc1","observation_id":"0fe90af3-bc98-49b5-b5fb-6cc7c79f7ff3","resolution":{"observed_at":"2026-08-10T14:48:58.379586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.361176Z","title":"Shield: Fast, practical defense and vaccination for deep learning using jpeg compression,","venue":null,"work_id":"c241c191-1b74-41ba-8acf-4b75d7083135","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.427711Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:ac5c7d6db2da87d76ad5bf5b27929dac3002cb5cd56b9ac171a7c5811ac76255","observation_id":"0d72511e-38a0-41af-a0e1-0d96cd06c6cc","resolution":{"observed_at":"2026-08-10T14:48:58.365738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.344452Z","title":"Defense for adversarial videos by self-adaptive jpeg compression and optical texture,","venue":null,"work_id":"77fa56a7-d570-40dd-88ab-d8d0cc01ed0b","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.431824Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:349b87d4ccad432855565c1a6ff4c437a994314881d5310c724e4bdb18fbf427","observation_id":"2e4d48f9-c39f-4d60-8ac3-59b2c6a001f7","resolution":{"observed_at":"2026-08-10T14:48:58.350476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.328434Z","title":"Temporal shuffling for defending deep action recognition models against adver- sarial attacks,","venue":null,"work_id":"5aab0b1a-89e4-4679-bf9a-11d61218cb5a","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.435824Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:ac46ef55ccc155e3bbd2ab69eca405dd0fd1cdb672176dace6f3b6346237e2ae","observation_id":"89633f17-8433-4423-a41e-825893951d1d","resolution":{"observed_at":"2026-08-10T14:48:58.333445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.309545Z","title":"Diffusion models for adversarial purification,","venue":null,"work_id":"9bd3c5c1-aecb-4a32-8a2d-1fedb6c93532","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.440191Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:d7254d27cbae1b536130a873d8a8d45741544ff30528f536837a77932d2c9d6a","observation_id":"f9060b8d-bd6b-4611-bd21-00c290314358","resolution":{"observed_at":"2026-08-10T14:48:58.314454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.288969Z","title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples,","venue":null,"work_id":"aad8d8c7-fbd5-4446-bc26-63837fa06875","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.444811Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:c42b26696f0d51cb4f3eba1896311453e450cad0a3aa394cb25f30a1cd4b073e","observation_id":"c7d0149b-7ce5-40ae-99df-d0dba432683a","resolution":{"observed_at":"2026-08-10T14:48:58.295305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.271454Z","title":"Synthesizing robust adversarial examples,","venue":null,"work_id":"e9d84d15-7386-46ce-b3b0-4c2d242d0d4d","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.449318Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:2f07797de116bbb3a5e157deefaa743765ac28501a4df83c2f2a58db495cf78e","observation_id":"37876f57-f152-4c3b-ac96-145716e92f54","resolution":{"observed_at":"2026-08-10T14:48:58.277100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.252525Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,","venue":null,"work_id":"cd59beb4-a0c9-4884-bbd3-8cb6f4e3229a","year":2020},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.454426Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:be7c8ceeea46e405cfec57f92c721d378ab7ee55348187e2eb0b58b27faec161","observation_id":"1f331525-e024-4651-8342-f81ad2e64319","resolution":{"observed_at":"2026-08-10T14:48:58.258556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.08089","last_updated":"2022-07-17T06:50:48Z","snapshot_observed_at":"2026-08-09T03:39:02.349909Z","submitted_at":"2022-07-17T06:50:48Z","title":"Threat Model-Agnostic Adversarial Defense using Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.08089","snapshot_observed_at":"2026-08-10T14:48:57.459111Z","title":"Threat model- agnostic adversarial defense using diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.459111Z"},"links":{"cited_paper":"/paper/2207.08089","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:9a6f8be3431c9b8be0b30f84a97054d3a097315970227f6b76f4688f936f9995","observation_id":"578b60d3-52e2-4774-9de7-25b2820b3bf6","resolution":{"observed_at":"2026-08-10T14:48:57.459111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10875","last_updated":"2022-06-22T06:55:03Z","snapshot_observed_at":"2026-08-07T07:03:58.487612Z","submitted_at":"2022-06-22T06:55:03Z","title":"Guided Diffusion Model for Adversarial Purification from Random Noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10875","snapshot_observed_at":"2026-08-10T14:48:57.463696Z","title":"Guided diffusion model for adversarial pu- rification from random noise,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.463696Z"},"links":{"cited_paper":"/paper/2206.10875","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:bf66bdebf1f436a131a31c7dc87f1db00a66abff6d5d592afc0e53dbe2db1d9d","observation_id":"3bfe0234-0321-40ff-b2ca-0c8d819a56b8","resolution":{"observed_at":"2026-08-10T14:48:57.463696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14969","last_updated":"2022-06-29T02:42:05Z","snapshot_observed_at":"2026-07-06T13:15:21.126555Z","submitted_at":"2022-05-30T10:11:15Z","title":"Guided Diffusion Model for Adversarial Purification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.14969","snapshot_observed_at":"2026-08-10T14:48:57.468719Z","title":"Guided diffusion model for adversarial purification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.468719Z"},"links":{"cited_paper":"/paper/2205.14969","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:bfce7e3a441a65faffb05d0bb0a35088a3c0903485e21bceb22d84e5a46764f9","observation_id":"98d7040a-20fe-4181-a01a-afb4509652d0","resolution":{"observed_at":"2026-08-10T14:48:57.468719Z","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":"2026-08-10T14:48:58.234370Z","title":"Enhancing adversarial robustness via score-based optimization,","venue":null,"work_id":"66917fd4-02e2-4566-874c-7b10a79a4eb2","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.473409Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:c665ab73062fb4e0d50e954b5fb34939615a78eb1b2a125551c37ea835edee6b","observation_id":"4c3eede9-0cee-447b-83d6-3bc58ace29d0","resolution":{"observed_at":"2026-08-10T14:48:58.241788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.217215Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":"8fefc4b9-2c74-4361-93b4-41b848679aa1","year":2020},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.478294Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:60e5248704faeabfc8ebf5d1e4f93e8cd68f48bb5b65f8cfce3b0f98dd5f57b3","observation_id":"83f75e84-2df0-4406-8c81-e17f93a8fde3","resolution":{"observed_at":"2026-08-10T14:48:58.222890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06571","last_updated":"2023-08-12T13:53:10Z","snapshot_observed_at":"2026-08-10T01:52:30.999213Z","submitted_at":"2023-08-12T13:53:10Z","title":"ModelScope Text-to-Video Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06571","snapshot_observed_at":"2026-08-10T14:48:57.482864Z","title":"Mod- elscope text-to-video technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.482864Z"},"links":{"cited_paper":"/paper/2308.06571","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:0556b30a82ce3fedae02790d286dc0c22219b3d25523a64b2748b3ca6748bd63","observation_id":"a3151141-35fe-4e00-b640-99f8254924d9","resolution":{"observed_at":"2026-08-10T14:48:57.482864Z","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":"2026-08-10T14:48:58.200358Z","title":"Denoising diffusion implicit models,","venue":null,"work_id":"afa40f2d-859b-448d-902f-af5359f31132","year":2020},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.487636Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:244ccb53adaec12ba9e1e6a8755c93184dfe388811438310514bfdae0eecc17f","observation_id":"60c4372d-858e-465d-b9ac-c218c9bed738","resolution":{"observed_at":"2026-08-10T14:48:58.206012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.183275Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":"ea67322c-17a0-4047-8e5f-71eaa8e03e04","year":2014},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.491658Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:aa5dffa48427c3d61ddb8bc460b65ffec2be7f81f44c91326671dc28bd2d5ba2","observation_id":"95532c82-d9c2-4d24-b144-dc2e80482ff5","resolution":{"observed_at":"2026-08-10T14:48:58.188661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.166408Z","title":"Boosting the transferability of video adversarial examples via temporal translation,","venue":null,"work_id":"daffa621-9f1b-4f4a-b962-0c7bf3c05190","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.495539Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:bb65d6a3a6873974b8d6a148e9066e062a30165b8ba62536b994267d943f7864","observation_id":"db155556-5feb-4238-809e-a250f2cd945f","resolution":{"observed_at":"2026-08-10T14:48:58.171398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.147102Z","title":"Global-local characteristic excited cross-modal attacks from images to videos,","venue":null,"work_id":"2d506d26-a828-4223-b2ba-b7f7c42ef811","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.499380Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:a340aaacd4a6d6e9b43ff484e6c45c6146eebf49fba24b1d4ce85d16e018382f","observation_id":"d0ad1e5c-bc92-45b0-9b8a-577d00719179","resolution":{"observed_at":"2026-08-10T14:48:58.154418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.128561Z","title":"Cross-modal transferable adversarial attacks from images to videos,","venue":null,"work_id":"06828bee-936c-45c2-8797-b6a6feb4293e","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.504157Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:54050285e0e0d545b27b7b9412b8635477351a2e35e325c2e4d2c4700b5537fa","observation_id":"ab761e5e-a164-4f71-b869-7c0cc7b55149","resolution":{"observed_at":"2026-08-10T14:48:58.134388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.110724Z","title":"Black-box adversarial attacks on video recognition models,","venue":null,"work_id":"cb0f4460-1344-432e-b1c7-602ba4e2d864","year":2019},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.509033Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:035c9fe3c742bf59118709839a6d3c37e8f0309be7cc0ffa0fee2e15418473f0","observation_id":"f95ea63a-935e-413c-a7f1-89a375810665","resolution":{"observed_at":"2026-08-10T14:48:58.116133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.093077Z","title":"Motion-excited sampler: Video adversarial attack with sparked prior,","venue":null,"work_id":"d1afe143-a1b0-4da3-ac6e-fbbdfc49af47","year":2020},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.513536Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:42771d5605af1d4a3a21045c4c7327051a6b83a83d055b573e9c8753e0b788bd","observation_id":"1b83e8db-c612-4f76-b4d6-3702753380ce","resolution":{"observed_at":"2026-08-10T14:48:58.098925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.066214Z","title":"Efficient decision-based black-box patch attacks on video recognition,","venue":null,"work_id":"cd8d3581-d184-4aba-92af-9bde1d9054db","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.518273Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:e4ac943b8f2c71e2d36ba6e3e8ebd7dc1af6bd8a22fa0939032c21cf6984c40e","observation_id":"812631fd-21ee-4cb3-8988-ec8a5b2a9c60","resolution":{"observed_at":"2026-08-10T14:48:58.071532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.051648Z","title":"Towards decision-based sparse attacks on video recognition,","venue":null,"work_id":"0d71628c-c7fd-4228-a33e-f5a6b9fac141","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.522720Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:0f06f9ced035d751fb43f2f8913a07814bf4ee96de9bd2f80d24504f28a4f585","observation_id":"09b9773d-46a5-4c5e-999d-faaba698a456","resolution":{"observed_at":"2026-08-10T14:48:58.056144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.527681Z","title":"Adversarial examples in the physical world,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.527681Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:302d773eaa492a7c85bafceacceaaf095353645618dc4bdb61982227c50d4c34","observation_id":"86f26413-c8ea-4ccb-a275-5f118b86e20e","resolution":{"observed_at":"2026-08-10T14:48:57.527681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-10T14:48:57.531914Z","title":"Adam: A method for stochastic optimization,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.531914Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:dbc75ad22c3d8dbbcf3c1e389304c298fb91ca5a110dc889bb96de33f1d8c6e1","observation_id":"8ac818fc-f7ef-4a05-b5d2-2cee7034d8bc","resolution":{"observed_at":"2026-08-10T14:48:57.531914Z","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":"2026-08-10T14:48:58.026247Z","title":"Just one moment: Structural vulnerability of deep action recognition against one frame attack,","venue":null,"work_id":"95d1799a-2432-4804-b82d-9795c0df3903","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.536448Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:66d475103fb23373b354c0afa56f2255f2b1906df75465558d3f693a4bb646be","observation_id":"a2cafcf9-308e-4281-9539-f1f6b0d9a1a3","resolution":{"observed_at":"2026-08-10T14:48:58.030968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:58.011093Z","title":"Over-the-air adversarial flickering attacks against video recognition networks,","venue":null,"work_id":"68c8503f-6506-4bc9-8613-13e93799b5aa","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.540858Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:e089d56000945c47dd46a87aa872316714b2fe8ac52d8ac42ad92742597ec99f","observation_id":"79179315-2d22-49b0-a65e-bf9949b6b640","resolution":{"observed_at":"2026-08-10T14:48:58.015521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.995378Z","title":"Diffattack: Evasion attacks against diffusion-based adversarial purification,","venue":null,"work_id":"9a719786-890b-4bfd-af1e-5343539a3013","year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.545212Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:5229cd181e506b1e3c39a3079a1153e0ebb3fbbc648ec20a0e11f63376a5f160","observation_id":"67e50031-3515-45e6-a9e7-7bbbf327ee20","resolution":{"observed_at":"2026-08-10T14:48:58.000207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-07-06T04:04:16.777653Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-10T14:48:57.550419Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.550419Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:f54b4a2b07cfff54ab264450add131a8d68ec1b7e5e20c65495e73eef5883015","observation_id":"37c71e83-9c3f-4caa-85c3-3dcb4bb3b37e","resolution":{"observed_at":"2026-08-10T14:48:57.550419Z","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":"2026-08-10T14:48:57.980429Z","title":"Image super- resolution as a defense against adversarial attacks,","venue":null,"work_id":"53803331-c964-49fb-89fe-bb1373e16a5e","year":2020},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.555100Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:cec49709f504937c2ee6510723f0c96d66e9351183b5c206557ce0164b733be4","observation_id":"b3ff5745-6739-4af7-970b-014bd0917e3a","resolution":{"observed_at":"2026-08-10T14:48:57.985129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.965401Z","title":"Taming transformers for high- resolution image synthesis,","venue":null,"work_id":"ddd9f77a-1d85-4fb2-b6af-71dee2995568","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.559572Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:6aa741bc0458218e64b063ec8f8f284ec75ed161975cc69ca9be9a287b38894b","observation_id":"bca7f215-d617-4df5-b449-186893f4c617","resolution":{"observed_at":"2026-08-10T14:48:57.970100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.950154Z","title":"Null- text inversion for editing real images using guided diffusion models,","venue":null,"work_id":"4c439e67-bdda-4978-b069-82cba74f8900","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.564313Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:0b1e51150acac86acf7b8b02e2d67dd3c999ef51b61843543cbf862b447b2098","observation_id":"da685d1a-d509-4a33-9dd1-88fec0b708fa","resolution":{"observed_at":"2026-08-10T14:48:57.955058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.934377Z","title":"Content-based unrestricted adversarial attack,","venue":null,"work_id":"36b4278a-4dcd-45fd-b808-d60800e9b6b4","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.568782Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:87d362ce33862f4ba3c246c2049339f088f31d697161f32596ec5957ca345f3a","observation_id":"fc398202-6ca9-4b7e-88ce-7f37fe850eff","resolution":{"observed_at":"2026-08-10T14:48:57.938848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17525","last_updated":"2025-03-11T02:16:29Z","snapshot_observed_at":"2026-08-11T07:46:04.646035Z","submitted_at":"2024-02-27T14:07:09Z","title":"Diffusion Model-Based Image Editing: A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17525","snapshot_observed_at":"2026-08-10T14:48:57.572647Z","title":"Diffusion model-based image editing: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.572647Z"},"links":{"cited_paper":"/paper/2402.17525","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:097b21c732b48913c348e62064d2795129b8e8c5d89cdfbb9d87799152472b18","observation_id":"bed7f4d2-731e-496e-822c-70122ea83b3c","resolution":{"observed_at":"2026-08-10T14:48:57.572647Z","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":"2026-08-10T14:48:57.919764Z","title":"Text2video-zero: Text-to-image diffusion models are zero-shot video generators,","venue":null,"work_id":"b58428ad-1114-4f1d-8bf3-6f52850d7dab","year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.576617Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:64c3879052387119b8e33e83377f947e32032707e697112e36eae46ff0d3f379","observation_id":"ce323eeb-4c3f-4eb0-ac86-743b53891540","resolution":{"observed_at":"2026-08-10T14:48:57.924278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00853","last_updated":"2024-07-12T13:55:40Z","snapshot_observed_at":"2026-08-10T12:06:43.562557Z","submitted_at":"2023-12-01T14:40:07Z","title":"Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00853","snapshot_observed_at":"2026-08-10T14:48:57.580422Z","title":"Motion-guided latent diffusion for temporally consistent real-world video super-resolution,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.580422Z"},"links":{"cited_paper":"/paper/2312.00853","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:0a4d319a3bb29266b2df9d3a4d806283249ef8afc2d08fc8593522e49b7bff27","observation_id":"b02063a6-45da-43ad-b06e-3e6b5154587c","resolution":{"observed_at":"2026-08-10T14:48:57.580422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-07-06T03:01:10.229407Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-10T14:48:57.585048Z","title":"Ucf101: A dataset of 101 human actions classes from videos in the wild,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.585048Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:3774265235d212a7dc8c8cb946f9b3e0db528f9a84a9fe3592435ddc3409bd89","observation_id":"4843206b-ff90-4d7e-b130-353c9abe9257","resolution":{"observed_at":"2026-08-10T14:48:57.585048Z","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":"2026-08-10T14:48:57.903979Z","title":"Quo vadis, action recognition? a new model and the kinetics dataset,","venue":null,"work_id":"fc8445c6-bc6c-49de-b1f3-fcfddfac99a6","year":2017},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.590208Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:0c36d63c7d82da490e006753c455e974f786f94d533a762f8eb20801c8cb9b35","observation_id":"cfd6c725-14a9-4c57-ba15-4243fccb68c7","resolution":{"observed_at":"2026-08-10T14:48:57.908948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.888281Z","title":"Non-local neural net- works,","venue":null,"work_id":"53ad04c1-7896-49ec-aea4-5efc7426688a","year":2018},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.596139Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:88bf7d277cbc31cc91bfcb66e9d512320ec9a8d7a79929de082217caa4aa3bff","observation_id":"4d4a0b40-a8a0-4b21-b848-4f4035e3ad0c","resolution":{"observed_at":"2026-08-10T14:48:57.893091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.873182Z","title":"Slowfast networks for video recognition,","venue":null,"work_id":"dfdb992b-f7b8-4bab-a732-94cd01952923","year":2019},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.601999Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:522a547d4edf6dfef54253ef6084926124eb929396b5defb253059d5d9be641e","observation_id":"bb5cfc41-af0d-4fda-9d2a-180ad669201a","resolution":{"observed_at":"2026-08-10T14:48:57.878183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.606320Z","title":"Raft: Recurrent all-pairs field transforms for optical flow,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.606320Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:63463f60322dcb1e16e63e0f323ba4bb26f78431a7324d73cbd50af39e3e6562","observation_id":"fd8e2888-cca2-438e-85f7-a07cbc9fb49c","resolution":{"observed_at":"2026-08-10T14:48:57.606320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06081","last_updated":"2018-03-22T12:46:44Z","snapshot_observed_at":"2026-08-09T07:48:15.268181Z","submitted_at":"2017-10-17T04:03:04Z","title":"Boosting Adversarial Attacks with Momentum","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06081","snapshot_observed_at":"2026-08-10T14:48:57.610259Z","title":"Discovering adversarial examples with momentum,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.610259Z"},"links":{"cited_paper":"/paper/1710.06081","citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:8f4dcdeac6638bc6c6531425ff252b378a1a08b3e640d7df6f3fa296b334d877","observation_id":"8f8830a6-f160-4fc2-9c37-6d4d37920a81","resolution":{"observed_at":"2026-08-10T14:48:57.610259Z","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":"2026-08-10T14:48:57.847792Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":"9916f9ad-2a61-49f8-8406-1d645f8996ba","year":2022},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.614469Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:f960a7a2af06d2876bf7b70fb41f557b628dc5727f25306591366e47f13fbc40","observation_id":"ad82d70f-36ea-404b-8fc5-15119aa451c3","resolution":{"observed_at":"2026-08-10T14:48:57.852970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:48:57.829984Z","title":"Diffusion models beat gans on image synthesis,","venue":null,"work_id":"c17762f4-764c-4dfc-99a9-0bb2087720a1","year":2021},"citing_paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T14:48:57.619008Z"},"links":{"citing_paper":"/paper/2501.14999"},"observation_digest":"sha256:be8fa06ebad62d733692b76eacbd410b5d7ec39821ceaaf91ee8a0267f1a057d","observation_id":"a3739b80-1aad-4e3c-b9ac-91410fbe8e90","resolution":{"observed_at":"2026-08-10T14:48:57.836319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.14999","last_updated":"2025-01-25T00:24:51Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T14:41:17.283051Z","submitted_at":"2025-01-25T00:24:51Z","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":51},"total_outbound_references":64},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2501.14999."}