{"as_of":"2026-08-08T16:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d2f99040a66a797f09b0d9e4e85da0cf1c2e396ef9385ecc83b8a5453477ec84","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:32:48.651115Z","state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.21742/citation-record","integrity":"/paper/2505.21742/integrity","json":"/paper/2505.21742/citation-record.json","paper":"/paper/2505.21742"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:32:58.910394Z","title":"Solving inverse problems with score-based generative priors learned from noisy data","venue":null,"work_id":"b6bc70e8-06bb-4885-b360-1f461d61fa9b","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.197511Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:873465d96154ed4af42614f998361843d1e257af08548608d04a180967247c58","observation_id":"be71c18a-64ed-4e44-8008-026f6ac5746f","resolution":{"observed_at":"2026-08-07T13:32:59.051102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:58.629078Z","title":"Extracting training data from diffusion models","venue":null,"work_id":"a932b24b-f45f-4144-b16c-0366037caee6","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.296601Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:9071ae042846bcb7ee9d354bf8cf1bbce35b8f5c0adfb29faa6398dec84ece45","observation_id":"212dd91c-1cf5-4de8-9b10-ab864549f0e3","resolution":{"observed_at":"2026-08-07T13:32:58.749214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:58.439827Z","title":"(certified!!) adversarial robustness for free! InICLR, 2023","venue":null,"work_id":"8e74b8ad-26de-4695-8562-3b0512c3c310","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.359136Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:8cf2b828cbd64e289d5326b2373f7206f6caec54b24b051e8bb48bea338f38d9","observation_id":"e28f4bf5-cad8-4701-8592-67146e1cf56f","resolution":{"observed_at":"2026-08-07T13:32:58.517124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:44.458482Z","title":"Perception prioritized training of diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.458482Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:e35a4890d3a3d1bbfca25b0072309d63913410ae17e9152c449e161b61188c8a","observation_id":"6878de3e-fefd-419f-ac75-b35a83c01ea5","resolution":{"observed_at":"2026-08-07T13:32:44.458482Z","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":"2026-08-07T13:32:58.254342Z","title":"Certified adversarial robustness via randomized smoothing","venue":null,"work_id":"8d989091-1d02-4d61-be02-e5cd79a96c96","year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.527558Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:7631e5c67cb9a9cfd5dcd7eb075aa71b374fe24a94c34a02db97e4fb6fe0337c","observation_id":"f82b856a-21b5-42ce-b47f-097881b6d157","resolution":{"observed_at":"2026-08-07T13:32:58.347819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:58.089859Z","title":"A high-quality robust diffusion framework for corrupted dataset","venue":null,"work_id":"f6908b39-3ca9-48e8-a60f-d144c0b78e5d","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.632921Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:97c77ad1ae126be8e99185a33f1f43dc0ec07cc554d7d103876caaba06c2ab6b","observation_id":"fb2df8f2-27e0-4581-b6ff-2b15e480b488","resolution":{"observed_at":"2026-08-07T13:32:58.162107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:57.871604Z","title":"How much is a noisy image worth? data scaling laws for ambient diffusion.arXiv e-prints, pages arXiv–2411, 2024","venue":null,"work_id":"9ad93254-7951-4718-a785-faee62568742","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.687198Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:1a4cc7b5e5d30cd9f482c0e14fc381300c2792c5b96cef731a986193cc045dec","observation_id":"ce52572b-68df-4547-804a-b452a3655090","resolution":{"observed_at":"2026-08-07T13:32:57.978915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:57.637268Z","title":"Soft diffusion: Score matching with general corruptions.TMLR, 2024","venue":null,"work_id":"aabb98f4-7986-41d1-98de-48604dfd913c","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.789811Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:567fb0afb2041ac50c9753aeedeb828f3007aa2b9b8a7c0decf8519fde09d958","observation_id":"f02b31f9-37ba-4a53-85db-6ff6c8cd775e","resolution":{"observed_at":"2026-08-07T13:32:57.759551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:57.435140Z","title":"Consistent diffusion meets tweedie: Training exact ambient diffusion models with noisy data","venue":null,"work_id":"2933a571-256c-470f-800c-3e83689f97c6","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.878326Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:82a18320badd950c39bf0deb0d44b833978963aea74f877104b8e49eea300a39","observation_id":"e1ac3c66-0a5e-4ec8-94c9-f839e16a09e7","resolution":{"observed_at":"2026-08-07T13:32:57.520326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:57.197274Z","title":"Ambient diffusion: Learning clean distributions from corrupted data","venue":null,"work_id":"bb30aa69-e50a-4afc-b104-5a3715ae06ce","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:44.940913Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:421d6274e9572a559117eb917b678c926e295445d994972192b81627b5c525f7","observation_id":"b5dc5f1e-d180-4edf-ad3c-ef23154cff88","resolution":{"observed_at":"2026-08-07T13:32:57.315250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:45.001779Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.001779Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:7361126e8e3c701e485e122cedbdb636392c8482eb19edc7bb059c1fbe621a55","observation_id":"6ea6326e-a208-420b-850d-912f9c66c958","resolution":{"observed_at":"2026-08-07T13:32:45.001779Z","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":"2026-08-07T13:32:56.976728Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":"9e6bbb6d-1675-4679-ae26-ce28e8173ccd","year":2015},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.054050Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:75f3e6b02c10d77cf99bc395aea7ae56b4deab37156e4254fab3305a2d9522b7","observation_id":"3961b074-69b1-4c68-ab7a-77f737d8020a","resolution":{"observed_at":"2026-08-07T13:32:57.073456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:56.737045Z","title":"Generative adversarial networks.Communications of the ACM, 63(11): 139–144, 2020","venue":null,"work_id":"fd5959c5-2e3c-4791-8f0c-5f405bf7289e","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.129535Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:78302d88a6c2028796615d39ef8934cd5068593cde98ab2edf92fdf43618446b","observation_id":"64f0d88d-227c-4e17-9e2e-02b56a9885aa","resolution":{"observed_at":"2026-08-07T13:32:56.852859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:45.184525Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.184525Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:26b00fd08069f6425d9e551b5fcc79b5d9c821aa249f38501be84c013ba4ff67","observation_id":"a17173ef-8ca7-4d21-9cae-6a81be5acd02","resolution":{"observed_at":"2026-08-07T13:32:45.184525Z","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":"2026-08-07T13:32:45.231883Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.231883Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:8d186eaabfc8fede1f2868a0d861eb8e72d3a1d194b7617c4d79227bc904699e","observation_id":"f0d93ebe-fd60-4efd-a9af-af3e792e2303","resolution":{"observed_at":"2026-08-07T13:32:45.231883Z","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":"2026-08-07T13:32:56.573311Z","title":"Adversarial examples are not bugs, they are features","venue":null,"work_id":"a5a1300a-1b1e-4625-84dc-52d44065d743","year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.285775Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:8d933df6ae0e82a1bdeeb5c3b36eb6457ddd7da89391f814be0b8bf4d8cab313","observation_id":"67379c4b-3422-4a7f-aaac-e0b2db5d6d74","resolution":{"observed_at":"2026-08-07T13:32:56.625664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:45.332878Z","title":"Measuring forgetting of memorized training examples","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.332878Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:8da4b589d4fbfdbd65e60149e3e268db165fa95ab3b5d75c61d21b4bbe2708fa","observation_id":"7afa5068-0702-467c-bb5e-d770168efe5d","resolution":{"observed_at":"2026-08-07T13:32:45.332878Z","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":"2026-08-07T13:32:45.392266Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.392266Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:3c850bb46f184a7a5c71eab9f88cf35c04d7f366ba2cf84046d5e6ba84e99a5b","observation_id":"2492fee6-307a-4cbb-a3ba-933327bebc28","resolution":{"observed_at":"2026-08-07T13:32:45.392266Z","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":"2026-08-07T13:32:45.451447Z","title":"Analyzing and improving the training dynamics of diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.451447Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:6467dae7db99f38bef6fd7b3d80944d6b6ece02404bd7f042f228201ec67a288","observation_id":"8df67601-8613-4126-ad83-11d8a3651e46","resolution":{"observed_at":"2026-08-07T13:32:45.451447Z","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":"2026-08-07T13:32:56.358259Z","title":"Gsure-based diffusion model training with corrupted data.TMLR, 2024","venue":null,"work_id":"d0d2e362-725f-4371-9f44-44edbaed6cf0","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.500146Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:199a0a942537ae8785ad5f8bbae38c515674b943c4081ee876301d27902b51de","observation_id":"7ef37455-f4ff-4fc2-b913-b6332ccb61d1","resolution":{"observed_at":"2026-08-07T13:32:56.448178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:56.197567Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"6dac5c19-debf-44bc-b07d-b4c94042fb95","year":2009},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.549801Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:306e1ef6f0d13b24773092eb8d77f65d0060a47a676c4fa336bdd953495bd80b","observation_id":"ad5b6d01-de2a-4e0f-a77f-3b52fe92c781","resolution":{"observed_at":"2026-08-07T13:32:56.258125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:55.988774Z","title":"Goodfellow, and Samy Bengio","venue":null,"work_id":"170bf6dc-2418-4987-93d6-5c9d70e16048","year":2017},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.612551Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:d893a69995856faf6ef2a56adf3f9a0167eda1418b8865c4265bfb36fcaa199c","observation_id":"1055881a-c2e8-436d-b4ff-90691ed93b26","resolution":{"observed_at":"2026-08-07T13:32:56.093820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:55.768871Z","title":"ADBM: Adversarial diffusion bridge model for reliable adversarial purification","venue":null,"work_id":"a522d235-5cbb-4418-bc2a-ee56704e366e","year":2025},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.685575Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:824e6c4468fbbd421f5edc49e0181f7d6ad13a7ffb2d308294f55238fca3614e","observation_id":"ab532e0a-acb2-479f-b9fb-a0cfe21cd592","resolution":{"observed_at":"2026-08-07T13:32:55.903407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.12962","last_updated":"2020-03-16T16:20:16Z","snapshot_observed_at":"2026-07-06T08:25:19.287839Z","submitted_at":"2019-09-27T21:26:34Z","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.12962","snapshot_observed_at":"2026-08-07T13:32:45.731516Z","title":"Celeb-df: A new dataset for deepfake forensics.arXiv preprint arXiv:1909.12962, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.731516Z"},"links":{"cited_paper":"/paper/1909.12962","citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:37ba905ecba7b6d03023ecf26ab7fa202a06b099c8a6c5e2c876612087e8f7ca","observation_id":"8c497927-4d2b-4117-8407-4754761e7e17","resolution":{"observed_at":"2026-08-07T13:32:45.731516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12683","last_updated":"2023-05-22T03:43:34Z","snapshot_observed_at":"2026-07-06T15:30:26.626858Z","submitted_at":"2023-05-22T03:43:34Z","title":"Mist: Towards Improved Adversarial Examples for Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12683","snapshot_observed_at":"2026-08-07T13:32:45.798501Z","title":"Mist: Towards improved adversarial examples for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.798501Z"},"links":{"cited_paper":"/paper/2305.12683","citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:ba68107d4d81163faec2181943a717fe09f1a4153b299dbc15a4a4c609bf4524","observation_id":"65ed769e-6785-4ada-b1e6-b09d63a9b5dd","resolution":{"observed_at":"2026-08-07T13:32:45.798501Z","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":"2026-08-07T13:32:55.579822Z","title":"Adversarial example does good: preventing painting imitation from diffusion models via adversarial examples","venue":null,"work_id":"479ebfec-8f05-4d41-bd83-5a51a063d738","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.853908Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:03cac29362cbaf6cf798938ecd03750a3361517229c305f22c05ec0c83483569","observation_id":"2bb464b4-f4db-4325-ae1f-005018d983a0","resolution":{"observed_at":"2026-08-07T13:32:55.665790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:55.380410Z","title":"Adversarial training on purification (ATop): Advancing both robustness and generalization","venue":null,"work_id":"1a3131d8-bf96-4e88-9446-7034282f5edf","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.916122Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:3d35155a4c238459ea9fa0c66006ae3a365fd8afc58509572ae13f487f84e272","observation_id":"af3e6548-7601-466a-8e15-9b4b3b14c7a5","resolution":{"observed_at":"2026-08-07T13:32:55.476836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:55.180219Z","title":"Towards understanding the robustness of diffusion-based purification: A stochastic perspective","venue":null,"work_id":"78abff5e-75c3-49db-987e-1b1a3d3dbede","year":2025},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:45.963929Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:63c3cbe3ca080e5dddce87b79d4b26f0053003a2b5f2cf265e6646bbc8aefea7","observation_id":"e56f86c6-8b30-4c2d-9d21-1ca26385c2c5","resolution":{"observed_at":"2026-08-07T13:32:55.257793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:46.010035Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.010035Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:6c32e39e572c6e65532bd6813c791dbe3250d32b6032541171a08bad60b541fb","observation_id":"5cc54261-78ff-43cc-b294-cfb4ef3e2320","resolution":{"observed_at":"2026-08-07T13:32:46.010035Z","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":"2026-08-07T13:32:46.060762Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.060762Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:20afde50fe8d7431615c7b90a91ce84a6e4270360d67be20584c15dd4860b63d","observation_id":"d1dd1831-ad18-423b-8a6f-31cb7ae82732","resolution":{"observed_at":"2026-08-07T13:32:46.060762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.10531","last_updated":"2020-07-22T20:24:17Z","snapshot_observed_at":"2026-08-05T12:54:50.372630Z","submitted_at":"2018-05-26T20:01:15Z","title":"Unsupervised Learning with Stein's Unbiased Risk Estimator","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.10531","snapshot_observed_at":"2026-08-07T13:32:46.117058Z","title":"Unsupervised learning with stein’s unbiased risk estimator.arXiv preprint arXiv:1805.10531, 202","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.117058Z"},"links":{"cited_paper":"/paper/1805.10531","citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:0261b4213e8dae3247fc9f3f2544ddd46f25b765ea5b23f62dc1286b4b1592ba","observation_id":"2e1871a6-634a-4cf1-8ddc-ca011764c389","resolution":{"observed_at":"2026-08-07T13:32:46.117058Z","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":"2026-08-07T13:32:54.880148Z","title":"Explicit tradeoffs between adversarial and natural distributional robustness","venue":null,"work_id":"b652df26-72ad-460f-8b9b-49c7416956b7","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.170354Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:f1b51bda6916abdf49ae7b5342acb357a4705f720fc46b2b9b3f51dac1026aa4","observation_id":"509ad66d-a2e2-48b8-b5f1-b5d1082590da","resolution":{"observed_at":"2026-08-07T13:32:55.007241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:54.610369Z","title":"A comprehensive study of image classifica- tion model sensitivity to foregrounds, backgrounds, and visual attributes","venue":null,"work_id":"2ef1f513-2643-43c1-a54b-0a13b4cee5e2","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.237847Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:417a1ce5b0d572cbd53e1aac481454ddd600cac9d239ee04348b9cef3e4316d4","observation_id":"3be3d780-c247-4801-a91a-7047d886cc5e","resolution":{"observed_at":"2026-08-07T13:32:54.724668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:54.345649Z","title":"Shedding more light on robust classifiers under the lens of energy-based models","venue":null,"work_id":"f89108a1-46e3-431d-a0e6-3698bab59654","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.281837Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:fb4326cdff04f212f95663693343d4d7139db79a9f999ab77b6ced6cfe771b67","observation_id":"54a62691-7755-4cca-af4c-85d8561051ee","resolution":{"observed_at":"2026-08-07T13:32:54.457116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:54.059122Z","title":"Spurious features everywhere-large-scale detection of harmful spurious features in imagenet","venue":null,"work_id":"f7a7b668-33a7-498b-9bcf-39966eecb24d","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.330628Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:8686495a8e91fa797dc7c8a4dae60ec3e96fd8669e5304b5353e05382d9ca5a2","observation_id":"35decd81-2817-4ad0-917a-21139a524509","resolution":{"observed_at":"2026-08-07T13:32:54.213926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:53.828603Z","title":"Adversarial Attacks, Regression, and Numerical Stability Regular- ization","venue":null,"work_id":"44788bac-cdc6-4caf-bc19-f3471d316278","year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.381483Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:5444b3b5aff06270f79bacde01c93855523957ccd8b2b34f8c0832e8c840f38b","observation_id":"09a24073-0f0f-4489-a651-1baae66fba8d","resolution":{"observed_at":"2026-08-07T13:32:53.943971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:46.427504Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.427504Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:b560aae7db81af6b8f39ca9312bd5671290fb4f2f5ff24ca8960252a4a0ad7a0","observation_id":"41d69b29-e2d9-40fe-b607-58d6c610cfa0","resolution":{"observed_at":"2026-08-07T13:32:46.427504Z","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":"2026-08-07T13:32:53.605762Z","title":"Diffusion models for adversarial purification","venue":null,"work_id":"872320ad-f12c-45ab-b4e0-fcb00e5d7991","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.460107Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:247d9725183af4680145d16b89ead6e99849fbee2429447d4c6b645c4c520635","observation_id":"655addf0-1b26-4d5e-96ce-d868fb05ec39","resolution":{"observed_at":"2026-08-07T13:32:53.698294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:53.325043Z","title":"Dinov2: Learning robust visual features without supervision.TMLR, 2023","venue":null,"work_id":"15245104-dbf0-4a2c-8eff-e4d7275e4f54","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.499461Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:639fb305aa49ef2d0ba6976fb5627a928c0a550792ffc5983beb985667358920","observation_id":"13114796-db8f-4fb3-b234-8229d1f5b2fb","resolution":{"observed_at":"2026-08-07T13:32:53.444420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:53.091292Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":"3c42a0a0-6804-415a-9084-6de755ca9009","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.540479Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:b467a10afd86548243b9fd080aad36f02d6225585e5cec39c7b0289b528eda90","observation_id":"29b93541-4bb8-4b13-97e6-75686be4f87e","resolution":{"observed_at":"2026-08-07T13:32:53.214354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:46.593366Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.593366Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:d34b16b98862977b9eb78ba17f0eb7a955586e3f44506decf3d4955da9329f4a","observation_id":"a0cc6ade-b5f0-4dbd-8ac3-395034d1e0e5","resolution":{"observed_at":"2026-08-07T13:32:46.593366Z","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":"2026-08-07T13:32:52.816445Z","title":"Improved techniques for training gans","venue":null,"work_id":"bd0944ac-2bce-4c79-be3e-3a44e3d9d036","year":2016},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.652051Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:b7cb2c7370c9612b78fed1863cbe21c0a4d23a97baa5f352523c941198bbc5ba","observation_id":"f2912690-160f-4b2e-b869-3e4e621d84bf","resolution":{"observed_at":"2026-08-07T13:32:52.955670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:52.531743Z","title":"Do adversarially robust imagenet models transfer better? InNeurIPS, 2020","venue":null,"work_id":"5d8a9900-bb66-431e-92b1-06f80565183b","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.694656Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:e66e0122fb1f9832ea928345d0c1417fd90bfaa5ecf64c4af8b7469c447a298b","observation_id":"20ce1444-6edb-46e0-9495-a0f507015491","resolution":{"observed_at":"2026-08-07T13:32:52.683832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:52.237594Z","title":"Denoised smoothing: A provable defense for pretrained classifiers.NeurIPS, 2020","venue":null,"work_id":"65fad29c-ae40-48bc-9acf-8981814d0035","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.730665Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:d1442e989b1441c4c5324e8debf46e400e8354af73ccc30ab0dc7eab5ec88df8","observation_id":"237de537-0a19-4da4-8d01-5fa91abad5dc","resolution":{"observed_at":"2026-08-07T13:32:52.377972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:46.771498Z","title":"Adversarial diffusion distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.771498Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:310d6c15138a8d05f8b1ad5499739832ab20f94d6e326c97d91a9a93bd428f86","observation_id":"7c481ecb-a24d-4494-abc7-a6f7ad1d71bd","resolution":{"observed_at":"2026-08-07T13:32:46.771498Z","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":"2026-08-07T13:32:52.013917Z","title":"Adversarial training for free! InNeurIPS, 2019","venue":null,"work_id":"f643434a-54c5-41f2-9274-0ed2e2d257d0","year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.811087Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:7cf89d8cdddb252e2ee3d34be1794b3efa1b9bf95ea590df2be17458d7fdc23f","observation_id":"42a440ca-d6d7-4671-a652-76132aa3cf57","resolution":{"observed_at":"2026-08-07T13:32:52.128599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:51.784029Z","title":"Salient imagenet: How to discover spurious features in deep learning? In ICLR, 2022","venue":null,"work_id":"0ef33775-8dc6-4750-97db-e8bd4c3f6296","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.854152Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:5c52970e1a6a087da0a450b4162794fb38480db2963e5bc3bd79785410737513","observation_id":"2ea9679d-5868-4a99-8ab6-d07fa19f1f04","resolution":{"observed_at":"2026-08-07T13:32:51.863667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:51.555150Z","title":"Diffusion art or digital forgery? investigating data replication in diffusion models","venue":null,"work_id":"27b5d5e0-a1ee-4a19-8e5d-bd366246a77c","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.903718Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:64afe8384720a8979fcd5ee04838a8027446e07841adcd3244eff0744cbf1f1a","observation_id":"f779106c-423f-488d-a0f4-9b9eabcbf24c","resolution":{"observed_at":"2026-08-07T13:32:51.672993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:46.994222Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:46.994222Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:16728488bec3347b62230f13a6ed49a3ac8da1c61bc844c8d41b0deb70be860e","observation_id":"68e90a0e-fe4d-4b1a-94fe-5654cb02251a","resolution":{"observed_at":"2026-08-07T13:32:46.994222Z","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":"2026-08-07T13:32:51.342372Z","title":"Mimicdiffusion: Purifying adversarial perturbation via mimicking clean diffusion model","venue":null,"work_id":"11948fa9-c81b-4736-95c2-84d4ab52b6cd","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.057806Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:6c071e83b1561895566a2abe935a9cce3d27e9770f16b91be79d27e5a4350c16","observation_id":"91122531-7f5d-4864-a16b-08651f6a8a5c","resolution":{"observed_at":"2026-08-07T13:32:51.427906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:47.144975Z","title":"Generative modeling by estimating gradients of the data distribution","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.144975Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:f26f959e4b02167c769a06c3807b88aecc7a697d7266a3740c5b40f96f75e647","observation_id":"5e337232-b27b-44e6-acbc-b208f6c2bd15","resolution":{"observed_at":"2026-08-07T13:32:47.144975Z","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":"2026-08-07T13:32:51.123042Z","title":"Pixeldefend: Leveraging generative models to understand and defend against adversarial examples","venue":null,"work_id":"2e346dea-752c-4be1-b9dc-d907e3ffa207","year":2018},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.207614Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:eeac27079a329453bf87b5f66ab80bcb9c7c2b79de38c25528fe573cb353e2b6","observation_id":"f0604c29-6ece-42f4-bba0-bc53f924bc05","resolution":{"observed_at":"2026-08-07T13:32:51.207393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:47.289816Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.289816Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:a8a283506f8d4d009f61b093e4327abee2d8b1d36152ffec1f1b0912979c122b","observation_id":"a49d51e5-f019-4ba9-95ec-dbc5d917f095","resolution":{"observed_at":"2026-08-07T13:32:47.289816Z","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":"2026-08-07T13:32:47.362078Z","title":"Consistency models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.362078Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:5e0874286773db0bb0bc1110af5d345d59669b66e884ab0e92a6d3274e97f6e9","observation_id":"6e698fa5-a988-47fe-998a-21e87e7417eb","resolution":{"observed_at":"2026-08-07T13:32:47.362078Z","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":"2026-08-07T13:32:50.916946Z","title":"Venkatesh Babu","venue":null,"work_id":"88dc3122-56d9-4adf-8e9a-b868b6a39378","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.436737Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:dc2ca2c4e5aac163d6196a91db91a8fa5457e08653acff07c3c2d7c75d4147ff","observation_id":"48e24e86-c482-4329-83ad-bf64c4c26978","resolution":{"observed_at":"2026-08-07T13:32:51.013329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:50.692459Z","title":"Towards efficient and effective adversarial training.NeurIPS, 2021","venue":null,"work_id":"fe1c3e40-33cf-480b-b5af-fa983b605622","year":2021},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.515475Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:1b82d01eba0d69fdcb6401efcbfdd46c18bc423ed7b88e913c796f4a6299143b","observation_id":"cec47b22-7b48-45aa-920d-a7baa64a9e0f","resolution":{"observed_at":"2026-08-07T13:32:50.821687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.01985","last_updated":"2025-02-11T18:09:35Z","snapshot_observed_at":"2026-07-06T19:09:50.836734Z","submitted_at":"2024-09-03T15:26:51Z","title":"UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.01985","snapshot_observed_at":"2026-08-07T13:32:47.602721Z","title":"Unsure: Unknown noise level stein’s unbiased risk estimator.arXiv preprint arXiv:2409.01985, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.602721Z"},"links":{"cited_paper":"/paper/2409.01985","citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:90d9dfeec01fc1d4399c36c0c96a92eb90bb2f063820639d5e7750ca61de76df","observation_id":"4bb9b2d8-27a3-4f6e-b70a-c96360b56c92","resolution":{"observed_at":"2026-08-07T13:32:47.602721Z","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":"2026-08-07T13:32:50.441718Z","title":"A comprehensive survey on poisoning attacks and counter- measures in machine learning.ACM Computing Surveys, 55(8):1–35, 2022","venue":null,"work_id":"5d0ae988-a05f-4680-b54d-1d10723af59a","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.661115Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:584907dc10b64384ddbe330eb39ed808e9d620996dac7085051df00cb831f6c0","observation_id":"21171bf2-606e-4b68-b36e-92cc1c509760","resolution":{"observed_at":"2026-08-07T13:32:50.566319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:50.293665Z","title":"Improving out-of-distribution generalization by adversarial training with structured priors.NeurIPS, 2022","venue":null,"work_id":"449723c2-2616-4520-9447-d59248995726","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.742976Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:a8fa07c580018dc577e6c04eb1ad9c30cf79ec40770232dee3298e625e653aec","observation_id":"e6298ab5-9259-41d9-8f6b-94181b6eda1b","resolution":{"observed_at":"2026-08-07T13:32:50.375944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:50.112181Z","title":"Improving adversarial robustness requires revisiting misclassified examples","venue":null,"work_id":"699d1793-9b18-4420-9fda-a6b9247c27e0","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.826792Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:75a92ef008eb412c0892798e7afd149975965d648166e17a1995d35917f40a13","observation_id":"e1869214-e170-436b-9ac5-ef42d4a4646f","resolution":{"observed_at":"2026-08-07T13:32:50.181478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:49.925850Z","title":"Better diffusion models further improve adversarial training","venue":null,"work_id":"1fca7d69-4c75-411e-b6d5-5fcaf028bec2","year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.891463Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:4a1c62367f774c89d2b14ba55b8d5eafe1fb3ee74a850ae9c191dac8e20678fa","observation_id":"5c9ae043-1bc1-409b-aa26-592d029b4bbf","resolution":{"observed_at":"2026-08-07T13:32:50.036291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:49.756733Z","title":"Fast is better than free: Revisiting adversarial training","venue":null,"work_id":"d03be81b-0202-45bd-8106-159ceaacf093","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:47.969123Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:054cbced7e699c96a30f324991e2a08ab32f38b5f41549df77ead64a505d8183","observation_id":"7869d8ea-fd45-4c01-a72f-78d8ea0ea841","resolution":{"observed_at":"2026-08-07T13:32:49.843996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.03018","last_updated":"2023-02-06T18:56:39Z","snapshot_observed_at":"2026-08-05T14:29:55.368812Z","submitted_at":"2023-02-06T18:56:39Z","title":"DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.03018","snapshot_observed_at":"2026-08-07T13:32:48.042452Z","title":"Ddm ˆ2: Self- supervised diffusion mri denoising with generative diffusion models.arXiv preprint arXiv:2302.03018, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.042452Z"},"links":{"cited_paper":"/paper/2302.03018","citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:15aa2edeabb1aed64c929eba28f729075506e069d1903423c56c08cf57e74174","observation_id":"12573fee-9605-469a-9dd6-525625f6e748","resolution":{"observed_at":"2026-08-07T13:32:48.042452Z","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":"2026-08-07T13:32:49.583450Z","title":"Structure-guided adversarial training of diffusion models","venue":null,"work_id":"385605f6-d00d-4f47-8bf4-5c516c0c14e4","year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.110539Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:1697f30dac1a7bf79b2094e9c5e49459d8d05a8223e882238da364633089e100","observation_id":"67a3333c-48f1-4c6d-a873-129f9e7688b8","resolution":{"observed_at":"2026-08-07T13:32:49.680930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:48.184873Z","title":"Spurious correlations in machine learning: A survey.arXiv preprint arXiv:2402.12715, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.184873Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:a7290f7946706b120def63e02c2544423d50aa4345fabd35873e6b7faa9b6b31","observation_id":"95492150-8ad7-4455-bdc3-fcd89ed428df","resolution":{"observed_at":"2026-08-07T13:32:48.184873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.03365","last_updated":"2016-06-04T09:51:30Z","snapshot_observed_at":"2026-08-08T13:26:17.517503Z","submitted_at":"2015-06-10T15:38:47Z","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.03365","snapshot_observed_at":"2026-08-07T13:32:48.249681Z","title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop.arXiv preprint arXiv:1506.03365, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.249681Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:0ac1ec60a7df2f959651c24c4dbba8f1e0377b9561e13e83d95a0e9e8a6fa67a","observation_id":"07d000ec-6393-4e0f-a1f9-4d807b257e09","resolution":{"observed_at":"2026-08-07T13:32:48.249681Z","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":"2026-08-07T13:32:49.424493Z","title":"A causal view on robustness of neural networks","venue":null,"work_id":"ed673e31-1db2-4fa2-8220-a1e09f093744","year":2020},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.327375Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:8901d3b28c1be2490d3b6a4f11e30deadca48c3cf4767c4010facc8c8ac99e1f","observation_id":"f22b55a0-d79d-43f6-9c76-47afc2d668e0","resolution":{"observed_at":"2026-08-07T13:32:49.511141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:48.391525Z","title":"Xing, Laurent El Ghaoui, and Michael I","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.391525Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:a4ece7620981b4ed4fa7c9aadb66a9a39e76e8b4e61ae2acbb64e909ea8d4fcb","observation_id":"87624f71-c3b9-4e51-867f-8d48e8877805","resolution":{"observed_at":"2026-08-07T13:32:48.391525Z","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":"2026-08-07T13:32:49.256989Z","title":"Adversarial robustness through the lens of causality","venue":null,"work_id":"96ab9a78-7728-46ab-be14-1cf709d63423","year":2022},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.467707Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:45989ee98c62eab04d564b8f44a1f2736dc0f67f06e3979c490a449deac42b5c","observation_id":"12e71a50-f96a-478b-80f3-65bdc204c6e8","resolution":{"observed_at":"2026-08-07T13:32:49.326666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:49.021069Z","title":"Rethinking generative mode coverage: A pointwise guaranteed approach","venue":null,"work_id":"2fc3328b-5f43-4b2f-9ca4-b5c3d5efaf7b","year":2019},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.565991Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:78b09444d0b62fe9aeb4fefe2e099736fdf7ee532741c346e3af71bb611aa227","observation_id":"539a904a-334f-4326-b2d4-c3c93283b620","resolution":{"observed_at":"2026-08-07T13:32:49.165321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:32:48.895901Z","title":"Towards understanding the generative capability of adversarially robust classifiers","venue":null,"work_id":"8071fe0c-53b5-47df-8bb2-c3d0db2a5d55","year":2021},"citing_paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:48.651115Z"},"links":{"citing_paper":"/paper/2505.21742"},"observation_digest":"sha256:edf8717933f153343efa4fff9f3be5bf2c0f1b44bdb5e156c684ff35d6ad9367","observation_id":"7fa45e0d-e02f-49c6-a744-ec3ffe340ef8","resolution":{"observed_at":"2026-08-07T13:32:48.952525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.21742","last_updated":"2025-05-27T20:32:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T13:21:41.109845Z","submitted_at":"2025-05-27T20:32:28Z","title":"What is Adversarial Training for Diffusion Models?"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":47},"total_outbound_references":71},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 0 inbound Pith citation observations for arXiv:2505.21742."}