{"as_of":"2026-08-16T12:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ec33d4168905b7a5a986234e8d1e77790d69509c59cecb7fd632f1fb4d3d558a","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T10:47:24.538466Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.18956/citation-record","integrity":"/paper/2411.18956/integrity","json":"/paper/2411.18956/citation-record.json","paper":"/paper/2411.18956"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.405292Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.405292Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:e21d83dcf5f486c965808e6432a53e31638f73a8af1cc24e6897eb17a8d2c94c","observation_id":"362e855b-a4c0-490e-ac0a-e49940645495","resolution":{"observed_at":"2026-08-12T10:47:24.405292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-12T10:47:24.409827Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.409827Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:7d0efe97988f720829ad0f4b439a03eda02e6e4d5ecb3473a630d1d9dd51e192","observation_id":"660f7639-1e1b-443a-98e3-2b0b55d12d61","resolution":{"observed_at":"2026-08-12T10:47:24.409827Z","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":"2026-08-12T10:47:24.926112Z","title":"Synthesizing robust adversarial examples","venue":null,"work_id":"1a671266-c7a5-4b6c-b5ff-72e8f6dcdb33","year":2017},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.413540Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:d1ba0a9ea5306e820b769e8ec61c8467a92b650a45e0a9195d0afce57ce7ea78","observation_id":"fcd862ca-c124-491d-b6f6-9379458f3ea2","resolution":{"observed_at":"2026-08-12T10:47:24.929675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.11655","last_updated":"2021-03-10T00:55:18Z","snapshot_observed_at":"2026-08-14T18:46:08.212239Z","submitted_at":"2018-07-31T04:18:26Z","title":"Security and Privacy Issues in Deep Learning","version":4},"cited_work":{"arxiv_id":"1807.11655","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.11655","snapshot_observed_at":"2026-08-12T10:47:24.637519Z","title":"Security and Privacy Issues in Deep Learning","venue":"cs.CR","work_id":"ea5d272e-0147-496f-b09b-05dbe0a82935","year":2018},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.418346Z"},"links":{"cited_paper":"/paper/1807.11655","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:704eb76ee289412afbb743a99efbd4dc6539e1525117a3bbcd67f6f47bacdedc","observation_id":"92220e3c-1095-44c3-9167-89c6ae7abb41","resolution":{"observed_at":"2026-08-12T10:47:24.642796Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.915413Z","title":"A survey of deep learning methods for cyber security","venue":null,"work_id":"b593c787-cf3a-492e-9fb6-944268c7de97","year":2019},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.422187Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:7222f1b85bc186019e547db62d3fe3ab6a5546b97419d71c1a2a226a16d527cd","observation_id":"b905cccb-ea7c-4a51-bd20-ab3103c93524","resolution":{"observed_at":"2026-08-12T10:47:24.919457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.904404Z","title":"Diffusion pos- terior sampling for general noisy inverse problems","venue":null,"work_id":"5bb2ca59-61f4-4c43-9057-5b3a9ef24fe3","year":2023},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.425550Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:ea1d2084d2e04af03856eb8af5c668fdcf4d7ea3ac2925923515c1b605da6fde","observation_id":"de55d680-c034-42b3-a721-60556541df31","resolution":{"observed_at":"2026-08-12T10:47:24.907905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.893125Z","title":"Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks","venue":null,"work_id":"009c85c0-3246-4622-af16-6450f6d1de3f","year":2020},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.428959Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:541f20a2abfbfdcd2af45304e4ae4a6efa3a8e7acfb1e6ab3bcaf17e3ff9606d","observation_id":"af841c6c-6473-4c73-b1ca-7f7264bf29bd","resolution":{"observed_at":"2026-08-12T10:47:24.896766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.882790Z","title":"Robustbench: a standardized adversarial robustness benchmark","venue":null,"work_id":"fdefed99-c5a3-43ad-933b-b9a4891d6457","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.432378Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:948ba12164ce139df0a08429db09870247565168fa09d40bd3c261676fa905ad","observation_id":"a5025691-4ebd-4363-a275-3391ea791be4","resolution":{"observed_at":"2026-08-12T10:47:24.886431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.872625Z","title":"Re- sisting adversarial attacks using gaussian mixture variational autoencoders","venue":null,"work_id":"0188cdb1-f0b6-4949-a433-13bc80cada9a","year":2019},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.435782Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:ce7d1718113dab9fa96cc5e3b6416da98a058a7cab622d59f673bc57c5b4e4e8","observation_id":"ef1b38d5-d091-477d-a926-469c089f6b6e","resolution":{"observed_at":"2026-08-12T10:47:24.876197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.862117Z","title":"Improv- ing robustness using generated data","venue":null,"work_id":"ad7f0900-2a45-499b-88fc-dcc9aadba749","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.438864Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:ca25bb396a478c44beb954b751f7708e657695e32c9a2fb508094e5432117de9","observation_id":"268eeae5-8ce4-4a4b-a4aa-0016b5156023","resolution":{"observed_at":"2026-08-12T10:47:24.865571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.442095Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.442095Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:2fdfd93344e1ad49426af94794e520ee8ac949f314e3e460897c1ae801688be9","observation_id":"779dc4c1-9a11-409c-ab1d-3f7e56e63e9e","resolution":{"observed_at":"2026-08-12T10:47:24.442095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.13525","last_updated":"2021-03-18T19:39:26Z","snapshot_observed_at":"2026-08-09T14:36:15.256747Z","submitted_at":"2020-05-27T17:53:36Z","title":"Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.13525","snapshot_observed_at":"2026-08-12T10:47:24.446229Z","title":"Stochas- tic security: Adversarial defense using long-run dynamics of energy-based models","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.446229Z"},"links":{"cited_paper":"/paper/2005.13525","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:db84757e5ccae18539c0383fa9e2d5b70ee6c997500487ae20aa3a507c0f6eef","observation_id":"8df67d41-a468-45f3-a666-95e86c4e0310","resolution":{"observed_at":"2026-08-12T10:47:24.446229Z","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":"2026-08-12T10:47:24.844211Z","title":"Stochastic security: Adversarial defense using long-run dy- namics of energy-based models","venue":null,"work_id":"aeb6d882-e4dc-420c-9bd3-b285d888e2a5","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.449644Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:eb04ee87fd9442044c75cc1e053d1d4278ec09410dd40f4a826fe44559b9d627","observation_id":"0bfd6e2b-0484-4a3c-b877-aae532c364fa","resolution":{"observed_at":"2026-08-12T10:47:24.848117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.834448Z","title":"DISCO: Adversarial defense with local implicit functions","venue":null,"work_id":"6ddcb1ec-0f62-4fd0-a8dc-1351300d4983","year":2022},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.453208Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:16111cc06f923db69f81d82676f727e32229fb472c9c01bf90b02447ee9cef75","observation_id":"e368f021-5a1c-41eb-91d1-7830a847b0f3","resolution":{"observed_at":"2026-08-12T10:47:24.838013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.457318Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.457318Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:bcee667dca1265fe812e0e5658b84f8981bf30f21f38b7f40633e5e6b01eddba","observation_id":"ebb72706-b706-4340-b1b6-a5bf00b4b8cd","resolution":{"observed_at":"2026-08-12T10:47:24.457318Z","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":"2026-08-12T10:47:24.818866Z","title":"Sta- ble neural ode with lyapunov-stable equilibrium points for defending against adversarial attacks","venue":null,"work_id":"aba472dc-84b3-4080-9cf1-e1a2888d8702","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.460743Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:743b084147ad61c33d29adb62f9ad02ce75d67bd6873e6576c6b08347de32fde","observation_id":"1e885606-d34b-4de2-9ec1-06370e577b94","resolution":{"observed_at":"2026-08-12T10:47:24.822743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.464021Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.464021Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:ea599f1018b1bd735c27cc4ba9ac5e3a5bb455ad139a4f243f1942286e222b26","observation_id":"95e6c587-35b8-4179-8c6e-3dfab051209e","resolution":{"observed_at":"2026-08-12T10:47:24.464021Z","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":"2026-08-12T10:47:24.801534Z","title":"Robust evaluation of diffusion-based adversarial purification, 2023","venue":null,"work_id":"01a6b1fa-0487-48a9-bc9f-23c45b0813ba","year":2023},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.467474Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:383510e83c2648b5599f1de5cc6134b04608882c45adb6583b92d6c518d1e93f","observation_id":"3fb15414-f297-4adb-8078-0ad45ce26710","resolution":{"observed_at":"2026-08-12T10:47:24.805097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.470422Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.470422Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:9368de84d4e904b0dad164e46e3eb49a1e8e7c259e698ee6f9e4ad1b0d169570","observation_id":"c9c6c89a-5f52-4f13-bafc-0b74c671e34a","resolution":{"observed_at":"2026-08-12T10:47:24.470422Z","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":"2026-08-12T10:47:24.473849Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.473849Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:966962da6371153245bf6ff94f1951be4b96d2019897f5461cb77130e1068a41","observation_id":"4ae3eea0-418a-4c47-9568-31fb136d91fb","resolution":{"observed_at":"2026-08-12T10:47:24.473849Z","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":"2026-08-12T10:47:24.784730Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"bb1df19c-b70b-4f4b-9e7b-c92203c0f8f2","year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.477788Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:156712c7afc6fe16df9e46f3fa62672e562e7c58bda086eb3030865d631912e3","observation_id":"806c6ff6-8044-4992-b809-1ef72da752ae","resolution":{"observed_at":"2026-08-12T10:47:24.788703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.03483","last_updated":"2017-02-27T05:47:30Z","snapshot_observed_at":"2026-08-14T21:35:40.472332Z","submitted_at":"2016-10-11T19:59:39Z","title":"Learning in Implicit Generative Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.03483","snapshot_observed_at":"2026-08-12T10:47:24.481149Z","title":"Learn- ing in implicit generative models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.481149Z"},"links":{"cited_paper":"/paper/1610.03483","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:ebb5beae074445354c0e4c9666ce6eb95b0c87708bd08d5b1c45b80a8da3523f","observation_id":"119b42ad-7483-4d89-b9bc-42a28b77a08d","resolution":{"observed_at":"2026-08-12T10:47:24.481149Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.07460","last_updated":"2022-05-16T06:03:00Z","snapshot_observed_at":"2026-08-15T17:35:42.005506Z","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":"2026-08-12T10:47:24.485280Z","title":"Diffusion models for ad- versarial purification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.485280Z"},"links":{"cited_paper":"/paper/2205.07460","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:66291925ff01e30d6d8fe1d83c7b710a4a9bdccdf7efc532ce32e95cb8203434","observation_id":"a7e0b7d3-3696-44a6-896c-674e5072c5c5","resolution":{"observed_at":"2026-08-12T10:47:24.485280Z","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":"2026-08-12T10:47:24.489051Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.489051Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:9f935893d68ccb4270fed0285603ea70d5d13d6adc93b56cdda4c54acc21d6f8","observation_id":"8c177e66-defc-400e-87b5-137b53966a85","resolution":{"observed_at":"2026-08-12T10:47:24.489051Z","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":"2026-08-15T23:59:07.582902Z","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":"2026-08-12T10:47:24.492591Z","title":"Defense-gan: Protecting classifiers against adversarial at- tacks using generative models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.492591Z"},"links":{"cited_paper":"/paper/1805.06605","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:93599794718fd08ebeb4dac2ee10d6e30c611f678fec15e59d3575d63abee7d0","observation_id":"99bf57e6-b85e-402e-a8f5-80ab7b56f4c5","resolution":{"observed_at":"2026-08-12T10:47:24.492591Z","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":"2026-08-12T10:47:24.767527Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":"4806ec92-f3d8-4278-bc71-6b5db3a20ae4","year":2020},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.496154Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:5334996d4b019d9830205ef2d1bad532cb583f104de9e4fdb5eb100388b17f02","observation_id":"9ce2c7fd-0a6d-43ca-8707-60414b2ad302","resolution":{"observed_at":"2026-08-12T10:47:24.770967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.757572Z","title":"Mimicd- iffusion: Purifying adversarial perturbation via mimicking clean diffusion model, 2023","venue":null,"work_id":"625be6ca-f3fc-4273-a961-2c0f00c0b3b1","year":2023},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.499058Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:f08d73227e1eeb37258f5ca815a4f0f44cad02150084b0e89e2157e766f216b8","observation_id":"ef5778f0-bdf6-4f3d-86f3-103ae683c3a0","resolution":{"observed_at":"2026-08-12T10:47:24.760982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.745867Z","title":"Pixeldefend: Leveraging genera- tive models to understand and defend against adversarial ex- 9 amples","venue":null,"work_id":"74958b1f-b5f8-42af-bfbe-7dbdebcd3c90","year":2018},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.502227Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:0fab86e2a2b10e5498ffbf87846d8799b7b8587c836240db9bd5cf758f1c6956","observation_id":"e2c182e3-186b-4a17-b17d-2019437e068f","resolution":{"observed_at":"2026-08-12T10:47:24.750120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.735543Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":"c2330513-4c66-4758-ae2a-b0b77c8ea84b","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.505834Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:9ee074576ec64b418cbaca227dbc52519a9e07cbaafbf9efe31754f543065b56","observation_id":"d0be5b1b-ad3b-4c71-91af-a58cdee88e7c","resolution":{"observed_at":"2026-08-12T10:47:24.739296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.726042Z","title":"Robustifying models against adversarial attacks by langevin dynamics","venue":null,"work_id":"9cbd8e2d-4854-402d-be8b-f9a1db4affdd","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.509286Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:79fa83dc2a408ba19d44a2f07ab8638ddfa6c1d26928e9d03a60d5784640f1bd","observation_id":"0497a455-3168-4b2c-a55a-e6f8720d55df","resolution":{"observed_at":"2026-08-12T10:47:24.729364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14969","last_updated":"2022-06-29T02:42:05Z","snapshot_observed_at":"2026-08-15T10:14:39.121914Z","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":"2026-08-12T10:47:24.512299Z","title":"Guided diffusion model for adversarial purification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.512299Z"},"links":{"cited_paper":"/paper/2205.14969","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:e08ce8ad2042e7cf2a3183196e49bf9d03788af867749c91cd71ed54e5cd0e30","observation_id":"c1d3f5d7-93b7-4747-adf8-e6828233d692","resolution":{"observed_at":"2026-08-12T10:47:24.512299Z","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":"2026-08-12T10:47:24.715479Z","title":"Deep face recognition: A survey","venue":null,"work_id":"653698d7-6ff2-41a3-b8bb-1fd9bb3a2b2d","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.515552Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:dd77d0a5855beb50255f1065b478d10ae28c1a16e2507032d388c6c03ebc61ea","observation_id":"e384af05-ec05-46d8-bc91-13eb7fb34fcd","resolution":{"observed_at":"2026-08-12T10:47:24.718902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.703506Z","title":"Adversar- ial purification with score-based generative models","venue":null,"work_id":"5261a024-6eae-41f8-b296-23dc639a807d","year":2021},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.518507Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:fc8db77ec2cf22b24ed5f2149ea85c43e5f7845db600be6719536482f5387b3b","observation_id":"6de9bffc-8e74-42cb-bc29-3ad955849e16","resolution":{"observed_at":"2026-08-12T10:47:24.707347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.09833","last_updated":"2023-03-17T08:38:33Z","snapshot_observed_at":"2026-08-13T12:22:50.689322Z","submitted_at":"2023-03-17T08:38:33Z","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.09833","snapshot_observed_at":"2026-08-12T10:47:24.521535Z","title":"Freedom: Training-free energy-guided condi- tional diffusion model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.521535Z"},"links":{"cited_paper":"/paper/2303.09833","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:9ea3aee83115beaadee855457dde02afe6888907a6f601db4ed63324698fc42d","observation_id":"2440d348-b9c6-402e-9a15-7398f84966c9","resolution":{"observed_at":"2026-08-12T10:47:24.521535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-16T07:54:28.918946Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-12T10:47:24.525439Z","title":"Wide residual net- works","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.525439Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:1fe92f10bce48dfbf7f996b19a306e6a9f061ca0fbecc9ff5dd89443550327a8","observation_id":"4253341d-ac7a-4342-965d-febc2180978a","resolution":{"observed_at":"2026-08-12T10:47:24.525439Z","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":"2026-08-12T10:47:24.692611Z","title":"Xing, Laurent El Ghaoui, and Michael I","venue":null,"work_id":"908d9091-b33f-4eaf-b159-fac0aeee5667","year":2019},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.529165Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:3035d25af21d05f47384e9eba2655e12f7e114334cf7ce59b815ca79691a9c73","observation_id":"28363145-ab00-4a2e-8f78-f98319332f65","resolution":{"observed_at":"2026-08-12T10:47:24.696695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.681942Z","title":null,"venue":null,"work_id":"e8fdeb9e-9924-48e1-80f4-f28cc6f9616b","year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.532080Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:35b7ffb0a579d66d70a805a86a6e29565399fc073758cf8234bb04db3a7fac02","observation_id":"8c8d29b9-7571-4251-b0b9-78330e834db5","resolution":{"observed_at":"2026-08-12T10:47:24.686054Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.670682Z","title":null,"venue":null,"work_id":"850969c5-21a7-4fd5-8e69-0ead1c2c278c","year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.535475Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:2d2725c653a605e106c5596cc9adcc57f8f0d7ae322072ed563787f373a75d61","observation_id":"1f9b2110-a597-4c52-94ff-2b9e437a3936","resolution":{"observed_at":"2026-08-12T10:47:24.674348Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:47:24.660704Z","title":"Thus, asynchronous attacks are in- troduced to challenge existing diffusion-based purification methods","venue":null,"work_id":"a5b970d9-7bea-4974-bc9a-e98a2fef7410","year":null},"citing_paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T10:47:24.538466Z"},"links":{"citing_paper":"/paper/2411.18956"},"observation_digest":"sha256:0cdeaf9d315193a92ac33990c9de1b388cf7d85d5bd379d683d337733ec37d8b","observation_id":"370c47b5-573b-4716-aca4-8e9b344280df","resolution":{"observed_at":"2026-08-12T10:47:24.663992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.18956","last_updated":"2024-11-28T07:04:09Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T20:20:45.182384Z","submitted_at":"2024-11-28T07:04:09Z","title":"Random Sampling for Diffusion-based Adversarial Purification"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":1,"verified_fuzzy":21},"total_outbound_references":39},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2411.18956."}