{"as_of":"2026-08-08T13:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f4e4da95df10a2e3c8749d81437b147b45c3874f961cd2496693310f9d615c37","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:00:08.189686Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"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/2506.03765/citation-record","integrity":"/paper/2506.03765/integrity","json":"/paper/2506.03765/citation-record.json","paper":"/paper/2506.03765"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:09.017410Z","title":"Explaining and harnessing adver- sarial examples","venue":null,"work_id":"6789a456-c81e-4e3d-a3f6-5fd0f030e577","year":2015},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.929867Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:35820c7b7e3d59618f5e230450e39a9683e9da0b3dbea4b3ef99aed85780d80e","observation_id":"7dda4e11-b6a8-4015-9864-07a6167b34cd","resolution":{"observed_at":"2026-08-07T11:00:09.023509Z","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":"2026-08-07T11:00:08.991321Z","title":"Towards evaluating the robustness of neural networks","venue":null,"work_id":"74904eac-28fe-41fa-a2a1-d52769e42f99","year":2017},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.937971Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:26cb7c48b552e119b11bffc7fe0a15746ec389d0fc11c9abfed81f04635a6945","observation_id":"72f6c914-85c9-44d2-aaea-74cd24efd2d1","resolution":{"observed_at":"2026-08-07T11:00:08.996530Z","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":"2026-08-07T11:00:08.975511Z","title":"Understanding adversarial attacks on deep learning based medical image analysis systems","venue":null,"work_id":"9c69d80a-faf0-4066-992c-68c2fd937520","year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.944223Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:e49f077d01ea2cd2b3d029779b7a60f66457b46e26760bceccb86165035aa27b","observation_id":"4c16475f-8ab8-40d7-bc1e-dbe8b9b7e1b0","resolution":{"observed_at":"2026-08-07T11:00:08.980686Z","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":"2026-08-07T11:00:08.959283Z","title":null,"venue":null,"work_id":"82e7f926-fcca-4080-a96c-56df3dd2d582","year":2024},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.952468Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:a25a793852f091d86eb96f2005b55c6325595b9b0a1bfe277f7d0bb47041f30e","observation_id":"2c0d560e-22ae-46a4-ae1a-475c9509c036","resolution":{"observed_at":"2026-08-07T11:00:08.963884Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-07T11:00:07.958874Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.958874Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:45c15141bb5a059211f1761d8915c1bb26f734d3dd18ae24a5c649b625848303","observation_id":"4c1da609-f2a6-4efe-8a97-ca51b328b54d","resolution":{"observed_at":"2026-08-07T11:00:07.958874Z","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":"2026-08-07T11:00:08.932088Z","title":"Fast is better than free: Revisiting adversarial training","venue":null,"work_id":"25571f87-1e39-4a53-9ef7-ff53656d332d","year":2020},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.967206Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:e35af4d703213c2610e7c4247ec357d063f79fe3f9ff7dc2330fcc0707da4283","observation_id":"67d1f0e4-57e5-4cbe-b1f6-0df00903b951","resolution":{"observed_at":"2026-08-07T11:00:08.937248Z","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":"2026-08-07T11:00:08.910736Z","title":"A comprehensive study on robustness of image classification models: Benchmarking and rethinking.International Journal of Computer Vision, pages 1–23, 2024","venue":null,"work_id":"b3f05832-3eb7-42e3-8030-84edb5e73592","year":2024},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.974612Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:6d85e91580abcf8d93f6ed3208dd9d3d0a1847740ed588468efe298ee892dcc5","observation_id":"2505b408-81b5-48de-8727-6ac5f79819d8","resolution":{"observed_at":"2026-08-07T11:00:08.917104Z","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":"2026-08-07T11:00:08.893531Z","title":"Feature squeezing: Detecting adversarial examples in deep neural networks","venue":null,"work_id":"bbe17071-7d48-41e1-ac26-92944246cb4b","year":2018},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.980229Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:57906c11dc0f466e4d9084726f9b192c598e132f62b70f1289f79f7fdae52e5c","observation_id":"40153afd-862a-43e7-9b9f-7881f87cc035","resolution":{"observed_at":"2026-08-07T11:00:08.898749Z","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":"2026-08-07T11:00:08.874846Z","title":"Detecting adversarial data by probing multiple perturbations using expected perturbation score","venue":null,"work_id":"cfb65fd0-ca6b-4cbd-bab6-9619cb391156","year":2023},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.985502Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:8018482689dabcfc55cea3a89507ce7a4e78b4c41b8388a9c96ca13f5592f43e","observation_id":"50c8d555-dcd1-4766-a924-7427714bbe5c","resolution":{"observed_at":"2026-08-07T11:00:08.880556Z","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":"2026-08-07T11:00:08.853851Z","title":"Detecting adversarial examples from sensitivity inconsistency of spatial-transform domain","venue":null,"work_id":"d444804a-70c4-4daa-9d21-e992ab3a5f03","year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.991580Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:e24f813f744c6ebdcee690ee127890f3ea966fc64c809aab16177daef4def46f","observation_id":"2ea7616f-3d23-4467-8527-c743faa3cbe4","resolution":{"observed_at":"2026-08-07T11:00:08.861131Z","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":"2026-08-07T11:00:08.836615Z","title":"Characterizing adversarial subspaces using local intrinsic dimensionality","venue":null,"work_id":"8d1a3c37-23b8-4d2a-92c4-31b293254a26","year":2018},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:07.998011Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:ad088e177d496c5a86e892de95e8f24c38a1e284c877e3810d1395fa21df5c29","observation_id":"803b742f-a03b-43f2-b034-048650d1e5f6","resolution":{"observed_at":"2026-08-07T11:00:08.841786Z","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":"2026-08-07T11:00:08.818481Z","title":"Detecting adversarial faces using only real face self-perturbations","venue":null,"work_id":"9aff819f-cd12-4e49-9eec-e2a4a38a8f42","year":2023},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.004307Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:c2a606125f46e1e8160e2d9eb654109e39e3e93cd4e2aace7b24bbedd04b1cd0","observation_id":"a31434a4-9fd0-4342-8c65-a24d2e239a6b","resolution":{"observed_at":"2026-08-07T11:00:08.824414Z","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":"2026-08-07T11:00:08.801232Z","title":"Detecting adversarial examples through image transformation","venue":null,"work_id":"9edd6a1f-8208-46fd-826d-42454ec296ba","year":2018},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.012739Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:80238ca4c5bf3bc5d72576044252c69226278bcff9e1bc0f7d87fcb39a27266d","observation_id":"02221bca-5e5a-4022-a0ba-fa871e6f2f4d","resolution":{"observed_at":"2026-08-07T11:00:08.806217Z","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":"2026-08-07T11:00:08.782854Z","title":"Adver- sarial example detection for dnn models: A review and experimental comparison.Artificial Intelligence Review, pages 1–60, 2022","venue":null,"work_id":"7d35e190-f21f-4970-b96e-9a914241ada2","year":2022},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.018253Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:569f5fac36fb941ea50f7315a23d0f3ff9d8380caa8a7dfbf8b5f5c8fd5b2a75","observation_id":"b948c1a4-87db-4423-aeca-f2dc31eb4754","resolution":{"observed_at":"2026-08-07T11:00:08.788536Z","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":"2026-08-07T11:00:08.766281Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","venue":null,"work_id":"f9fabf58-282e-43cf-bb3c-1fb8fa0526c9","year":2020},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.026654Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:cbb4dd04f1f09ee7f35939b6dde4cbaede760fce80fca2ae8b4b33ccb9a25cdc","observation_id":"67894547-a684-42fc-a905-18bc4fb9dfe8","resolution":{"observed_at":"2026-08-07T11:00:08.771619Z","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":"2026-08-07T11:00:08.750592Z","title":"Minimally distorted adversarial examples with a fast adaptive boundary attack","venue":null,"work_id":"5a60c92a-b0df-48d3-b0e8-2e4d688da437","year":2020},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.039317Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:f9a1af0f6592dccf2f7b2457b844af28697355f8fdd7ccb532ba5eacf8c6661d","observation_id":"6b709e36-8c57-4183-8a9b-acef2fd58ac6","resolution":{"observed_at":"2026-08-07T11:00:08.755754Z","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":"2026-08-07T11:00:08.733246Z","title":"Square at- tack: a query-efficient black-box adversarial attack via random search","venue":null,"work_id":"1ecb5eae-ec67-490c-b9c1-322843161b64","year":2020},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.044841Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:cfe873d88092afd9e6d94055ea7bd96cf55e55c5c6eab8edd3a8fcab9e4d475d","observation_id":"82e54c4c-081e-4ce2-9a46-d7ede4ee62dc","resolution":{"observed_at":"2026-08-07T11:00:08.738616Z","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":"2026-08-07T11:00:08.049394Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.049394Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:f476a6b6bb63ce5cf3cd878428550e71ff1c95f4de6231b58a4944d735f007ab","observation_id":"a92459f4-f5fa-453c-a1f4-798b5ab9841e","resolution":{"observed_at":"2026-08-07T11:00:08.049394Z","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":"2026-08-07T11:00:08.704647Z","title":"Deepfool: a simple and accurate method to fool deep neural networks","venue":null,"work_id":"6db5a432-c08e-489d-9fdd-e1e1fed6e045","year":2016},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.054270Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:a352b826e3b40fc29c58b46cff45b3a862b2199d2a6c5c87d9e08be648246cd6","observation_id":"b2c5bbbb-ed16-4874-a41f-7b5ee311f8e3","resolution":{"observed_at":"2026-08-07T11:00:08.709851Z","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":"2026-08-07T11:00:08.686621Z","title":"Triangle attack: A query-efficient decision-based adversarial attack","venue":null,"work_id":"22954281-c077-4b82-9491-3f84ef53e958","year":2022},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.059025Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:d1cea535a20e8c895dfa531acaf99c2a87f5f889daef42c7a75c7299df3e5e39","observation_id":"1a2c677c-4561-4683-87d9-bf52606b2292","resolution":{"observed_at":"2026-08-07T11:00:08.691791Z","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":"2026-08-07T11:00:08.064720Z","title":"Enhancing the transferability of adversarial attacks through variance tuning","venue":null,"work_id":null,"year":1924},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.064720Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:ad08efa9e6a9a7249355a2d4429497fdb4b2d5e90b619439dca55ec11b51df00","observation_id":"38ae3260-21e2-4dfe-b44a-31d23f60b074","resolution":{"observed_at":"2026-08-07T11:00:08.064720Z","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":"2026-08-07T11:00:08.650917Z","title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","venue":null,"work_id":"76ba0bae-02ba-45f0-8086-6320675306ab","year":2019},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.069883Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:f6883ae75a9ab99d3557937e3ba5206f97a88a0257982615a95f4a3c4299cfd7","observation_id":"6e2182fe-5357-4d63-82a2-7a5a066e6313","resolution":{"observed_at":"2026-08-07T11:00:08.656605Z","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":"2026-08-07T11:00:08.079792Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.079792Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:f3912a0edf1414656415d89a6bcb40b3dea151baeb8599c1ca4fe5e2d16f202d","observation_id":"0b09bd2c-63a3-432a-97ba-a6e23f18936d","resolution":{"observed_at":"2026-08-07T11:00:08.079792Z","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":"2026-08-07T11:00:08.087132Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.087132Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:e618848be6c509a55def1d3b79d66e8b0fa0960e882d1d46ee01f0475d642a90","observation_id":"d3245452-2c01-4f29-b54f-4c201f12ff2d","resolution":{"observed_at":"2026-08-07T11:00:08.087132Z","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":"2026-08-07T11:00:08.092363Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.092363Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:5ad94bdfeb25df145d44b593b88e1939d4d12493579b47a3d2193e2ef2ba4a2f","observation_id":"9fbd5944-2fa1-4ce8-a5bd-f7de4e597c8d","resolution":{"observed_at":"2026-08-07T11:00:08.092363Z","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":"2026-08-07T11:00:08.574958Z","title":"Improving fast adversarial training with prior-guided knowledge.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024","venue":null,"work_id":"c281f1d0-5601-482f-830b-bcaab84723e2","year":2024},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.098110Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:4bf06baeffe2f0972456b1afa839401fa07869f1425d7fe32c6986204dd8200e","observation_id":"279ead43-5077-41b6-8e1a-7f544c5c09b2","resolution":{"observed_at":"2026-08-07T11:00:08.584209Z","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":"2026-08-07T11:00:08.557628Z","title":"On the robustness of vision trans- formers to adversarial examples","venue":null,"work_id":"3017c93b-f036-4eb7-b15c-74b86be8dbcd","year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.104653Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:c0549bb8dcbb5a81d9072ebf77c999634d51a40a0bacae4417ba2f80a2ace8ee","observation_id":"8093b998-03ef-4af6-99cb-a2d61b10bf9d","resolution":{"observed_at":"2026-08-07T11:00:08.562699Z","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":"2026-08-07T11:00:08.109396Z","title":"Foundation models defining a new era in vision: a survey and outlook.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.109396Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:99be90d87fdb8ca853483423ffbcf47b60c1d9cc7157c947c0af2e06f32fb31f","observation_id":"2ff9daa6-5724-4439-ac0c-c3d94c36de6c","resolution":{"observed_at":"2026-08-07T11:00:08.109396Z","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":"2026-08-07T11:00:08.115200Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.115200Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:c69a74603826577d446a19ae7bef80772778777692dfaeea58227aa07753f658","observation_id":"17ccb9e9-c679-4f23-856b-3607cde82021","resolution":{"observed_at":"2026-08-07T11:00:08.115200Z","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":"2026-08-07T11:00:08.508720Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":"e0d53541-3db4-43d0-b14a-a1a800abb38e","year":2009},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.124667Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:c18857b92339ff1d0f542ec99d035458a54fcd6e39735e0877d8a6454d6bf482","observation_id":"d58fa7f0-95e0-455d-9c62-29a66f3ff07e","resolution":{"observed_at":"2026-08-07T11:00:08.514343Z","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":"2026-08-07T11:00:08.130700Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.130700Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:d63f2b447fdd9d44bb6c44710e481b1e0ec1d28d032f9ebde27dea490dce4d7c","observation_id":"96e5f109-d4da-480a-9dc4-b0c4df8fb515","resolution":{"observed_at":"2026-08-07T11:00:08.130700Z","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":"2026-08-07T11:00:08.136042Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.136042Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:bf101d696f8e2d4d88c3274baf291ab8770160f0e1a7530c1479051abd281594","observation_id":"62c8dd9a-fdba-4d8f-8c46-346f3a157644","resolution":{"observed_at":"2026-08-07T11:00:08.136042Z","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":"2026-08-07T11:00:08.460937Z","title":"Diffusion models for adversarial purification","venue":null,"work_id":"3afc3d3b-0f48-49ef-89e0-e1eec491c7f1","year":2022},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.145831Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:8571f5fdfdb54950a63458a1000a08522abc4290a76d12b65475afe5182bc948","observation_id":"a4141720-0a0e-4716-bfe3-57cc63f0824d","resolution":{"observed_at":"2026-08-07T11:00:08.466689Z","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":"2026-08-07T11:00:08.152227Z","title":"Denoising diffusion probabilistic models.Advances in Neural Information Processing Systems, 33:6840–6851, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.152227Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:12cbaa5a8d19abcd7de8b850424df8bae22aa6f336c2ae67164fac6d4f5c0459","observation_id":"582ffa53-6919-495e-9360-98403bf967b7","resolution":{"observed_at":"2026-08-07T11:00:08.152227Z","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":"2026-08-07T11:00:08.427946Z","title":"Robust models are less over-confident.Advances in Neural Information Processing Systems, 35:39059–39075, 2022","venue":null,"work_id":"898338cf-954a-416e-aa36-89dcb6e601ce","year":2022},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.160180Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:b2624cca2b788236261e1dcb2df8a307503b3f715fe6713aeea072bb3940f1cd","observation_id":"f2cdffe2-e6ea-49ee-b861-85f3930c2a6d","resolution":{"observed_at":"2026-08-07T11:00:08.435308Z","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":"2026-08-07T11:00:08.402844Z","title":"Evad- ing adversarial example detection defenses with orthogonal projected gradient descent","venue":null,"work_id":"581ddff6-6686-4789-a057-4f783ec4ea55","year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.165185Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:2309e7ff649a44aea3aa0f2ecdec9fa851fd9c499932a6faba9a0e9b3a844370","observation_id":"ad425545-e183-4db7-90fd-377dd4bcf984","resolution":{"observed_at":"2026-08-07T11:00:08.411780Z","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":"2026-08-07T11:00:08.170202Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.170202Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:e1a9c5fd1e6404480c394407154274e7c71205764f2823ce21a05a1fbabcac52","observation_id":"da3adc30-68f0-4cd7-b923-cb56051ef91b","resolution":{"observed_at":"2026-08-07T11:00:08.170202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01950","last_updated":"2021-02-19T15:42:38Z","snapshot_observed_at":"2026-08-04T22:49:29.740804Z","submitted_at":"2020-09-24T01:34:42Z","title":"Torchattacks: A PyTorch Repository for Adversarial Attacks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01950","snapshot_observed_at":"2026-08-07T11:00:08.176290Z","title":"Torchattacks: A pytorch repository for adversarial attacks.arXiv preprint arXiv:2010.01950, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.176290Z"},"links":{"cited_paper":"/paper/2010.01950","citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:f5947b9e29c4e82541f82b0d495affd3bb043844c289d02beb0e1953de5c6274","observation_id":"5d43278b-2bef-4578-9fa2-5ee947091ea9","resolution":{"observed_at":"2026-08-07T11:00:08.176290Z","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":"2026-08-07T11:00:08.372179Z","title":"Benchmarking adversarial robustness on image classification","venue":null,"work_id":"ee81a37a-1f51-4a9d-b945-62a2dbb11abf","year":2020},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.183203Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:8eb30b2e1ca4425999749e9023137a1196922fa514ac66fa79859f28c57c3c3c","observation_id":"d1ed238a-e32f-4499-a136-cb6365563619","resolution":{"observed_at":"2026-08-07T11:00:08.378548Z","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":"8198.5499","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:08.318805Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":"427b84a9-5e71-4a9f-afc3-f4ee5bf42b55","year":2021},"citing_paper":{"arxiv_id":"2506.03765","last_updated":"2025-06-04T09:29:11Z","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:08.189686Z"},"links":{"citing_paper":"/paper/2506.03765"},"observation_digest":"sha256:b04350d36d35d75a03e65b1eb4fa18fc730199fd92f4c8b7f397376f3e72566a","observation_id":"ec239471-69a3-4f5d-8549-01f2717ee8b2","resolution":{"observed_at":"2026-08-07T11:00:08.332773Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2506.03765","last_updated":"2025-06-04T09:29:11Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T10:53:14.603409Z","submitted_at":"2025-06-04T09:29:11Z","title":"Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":25},"total_outbound_references":40},"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 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2506.03765."}