{"as_of":"2026-08-08T02:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4294dab57df1aa331d0f49bc4b7ae7fdf66314580cd69f750d42681fe5c292ed","coverage":[{"denominator":77,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":77,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:13:02.411975Z","state":"measured"},{"denominator":77,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":77,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2505.22486/citation-record","integrity":"/paper/2505.22486/integrity","json":"/paper/2505.22486/citation-record.json","paper":"/paper/2505.22486"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:16.788355Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":"2da4ef3f-8a41-441d-97fc-c75819a050b8","year":2014},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:54.889256Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:6aac3dab96b940cf92a485b7f9051d4cccba8cfd7eded6198f16f397eca0cae8","observation_id":"3daa1341-76a6-4fe0-8efa-e2b666690419","resolution":{"observed_at":"2026-08-07T13:13:16.898439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:16.565124Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":"b420afa0-9560-4c2b-9e90-dc726bcb1cd0","year":2015},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:54.955197Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:6d1905bb20e54c36f6059a56b818a8d420f70d8b5685cce03d4e01e324f1f122","observation_id":"575eff68-ad8c-443c-97bb-41bee41399e2","resolution":{"observed_at":"2026-08-07T13:13:16.698856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:12:55.078223Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.078223Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:3543d00626f086b2a5fc1b8f695b204b0f9d55287e11307612fec982a909ee18","observation_id":"289c0cc1-1926-44ad-bb02-f49f4834860f","resolution":{"observed_at":"2026-08-07T13:12:55.078223Z","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":"2026-08-07T13:13:16.332658Z","title":"Theoretically principled trade-off between robustness and accuracy,","venue":null,"work_id":"fa5328c2-7852-444a-b74f-9ddb7678a419","year":2019},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.231883Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:7475c0e724074b99d8b29e5f25229443b8647f3c7200758acaf701ba8844f123","observation_id":"f5c531fb-9be5-4bb8-96f5-aa6a8d392145","resolution":{"observed_at":"2026-08-07T13:13:16.460146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:16.133443Z","title":"Adversarial training for free!","venue":null,"work_id":"301a0678-0c94-4083-9de2-ec065f0c26fe","year":2019},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.394017Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:bbc33aff66b3294fba9445d43e85ffa35263b5543907a5cf278de6bb74e69b0b","observation_id":"8dd67d73-c669-4a70-b2c3-82ae4b63d0ce","resolution":{"observed_at":"2026-08-07T13:13:16.219738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:15.874952Z","title":"Fast is better than free: Revisiting adversarial training,","venue":null,"work_id":"a319cf7c-9ed9-4fb4-a5c6-ee26473673c0","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.545875Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:a7f5e27b1fc82635b00cd0fb2e9eaddf5b0bcbc22c25cef4da9337529b0031d7","observation_id":"4c62b045-c62b-495a-a5cd-aee97c8f778d","resolution":{"observed_at":"2026-08-07T13:13:16.016483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:15.658270Z","title":"Improving adversarial robustness requires revisiting misclassified examples,","venue":null,"work_id":"a7e3b659-e9d2-4ac7-bed4-cfbe3dbd06bb","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.650640Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:8900f1da2743fb5f93100907d14f730a382d06c65e2650d00b56c9517270dc74","observation_id":"9d225a32-e52c-45f1-ad9d-5a341a7a890d","resolution":{"observed_at":"2026-08-07T13:13:15.791959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:15.442131Z","title":"Towards efficient and effective adversarial training,","venue":null,"work_id":"8df58bbd-e9b7-4d5c-88fc-9d8ab3672aa6","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.773679Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:109be056acac8b567f0b69aba4cd84c129cc5f7e0871e9385cc1f0510b317dbb","observation_id":"3acf2d8a-5b9e-4567-9ead-2a64f4f9ec30","resolution":{"observed_at":"2026-08-07T13:13:15.579134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:15.222023Z","title":"Guided adversarial attack for evaluating and enhancing adversarial defenses,","venue":null,"work_id":"6d63c671-b17e-49d2-86ed-94be289b05be","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:55.911042Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:8c006e64f26d136d069cd11fece47d1c9d5e91897600c77f382ae0baec836f45","observation_id":"4644f834-29c3-48f6-9e80-b56ef1a3a69c","resolution":{"observed_at":"2026-08-07T13:13:15.309458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:15.006516Z","title":"Unlabeled data improves adversarial robustness,","venue":null,"work_id":"0157ba9c-5d75-4ab8-9b69-c2148ec0c41d","year":2019},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.021136Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:28b44151fa97f9f3558a4982e72a942ed3821eaa3962464c86c0085cfdcc0c7c","observation_id":"b7ea4964-8bf4-4a0a-92c7-716c2877e959","resolution":{"observed_at":"2026-08-07T13:13:15.127189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:14.781547Z","title":"Improving robustness using generated data,","venue":null,"work_id":"51687b5c-38f0-4cb2-a207-7418284c2499","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.142611Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:d275c35ba74de4b61ce67654a43450766cc66aece80fd6a1fb04c80b2901e6b8","observation_id":"6d231bfe-6cd5-4d2a-8d07-4bb15cc4c303","resolution":{"observed_at":"2026-08-07T13:13:14.902012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:14.563550Z","title":"Better diffusion models further improve adversarial training,","venue":null,"work_id":"10feb75a-0ed3-41fd-83e0-8eead16aca15","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.298658Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f4a77f084296cc639984fefd17db8a29474938901242fbf342617c8b8588a7ed","observation_id":"965980e8-288f-4b19-8e99-ea0cb7e2022a","resolution":{"observed_at":"2026-08-07T13:13:14.679269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:14.232996Z","title":"Probabilistic margins for instance reweighting in adversarial training,","venue":null,"work_id":"ffd749db-7f0a-4590-8217-50c7fd8d6141","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.390259Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:bf4089edfb2f52343811beffb6fd1fb228a9fe24bf3c1d717b8e9b3d2f89f950","observation_id":"3e35785c-b550-49b3-a167-5a894cf71e75","resolution":{"observed_at":"2026-08-07T13:13:14.414264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:13.914643Z","title":"Overfitting in adversarially robust deep learning,","venue":null,"work_id":"15af1167-d184-4409-9eaf-c5e4131bb609","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.478081Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:bb581c2699fa99367510f1013c462ad394d7ac72253f99334cbf2653ee85dd4a","observation_id":"829ff276-75e3-449f-9e83-a151a7fed270","resolution":{"observed_at":"2026-08-07T13:13:14.049169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:13.624876Z","title":"Shedding more light on robust classifiers under the lens of energy- based models,","venue":null,"work_id":"68a6d36a-67c4-463b-aa41-cc6fe97e5674","year":2024},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.587584Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:8c5c65e970aa2c0fadd307ecef12c09ba3f8785e0adea523388ca66bf9d1e4e0","observation_id":"4d5899ce-6005-411f-b1d8-37c7421ba604","resolution":{"observed_at":"2026-08-07T13:13:13.786698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:13.350714Z","title":"Understanding catastrophic overfitting in single-step adversarial training,","venue":null,"work_id":"e0baf382-e999-448a-97d1-39faeb034ae2","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.708272Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:d4e9279e39021aa7feacae238ad2351670733f967b5d0bb40bedf0ab1e423665","observation_id":"c6209312-ac54-4049-97b4-747bf35ce257","resolution":{"observed_at":"2026-08-07T13:13:13.471296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:13.116626Z","title":"Robustbench: a standardized adversarial robustness benchmark,","venue":null,"work_id":"76cfa2b4-6dde-482f-aca3-f36f899eab51","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.790871Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:87c8285166f073c75ed4866e53a009e1b60e8040958ce5de3dacb62ad6a7ad86","observation_id":"99827548-b776-4556-894e-db01d987bf72","resolution":{"observed_at":"2026-08-07T13:13:13.238576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:12.783643Z","title":"Robust principles: Architectural design principles for adversarially robust CNNs,","venue":null,"work_id":"a0a48cbc-a70f-4952-bec9-c2c1fd0e5f88","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.881019Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:c41cb0d51796e27f55d7ea1dad64383f296647d86dd07f7788197ecea2a8e52b","observation_id":"412921ce-0679-4b06-b3c0-327aa74319d4","resolution":{"observed_at":"2026-08-07T13:13:12.967858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:12.424044Z","title":"Adversarial weight perturbation helps robust generalization,","venue":null,"work_id":"fa06e4b8-f3a6-4f60-9bd8-7b156e30fe28","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:56.988438Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:94d994f353e573802408243c9811c7890e5c9bff0272b6a15248929697300a7c","observation_id":"951d45e5-64ab-492d-87a5-03d286d07bd8","resolution":{"observed_at":"2026-08-07T13:13:12.590286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:12.111432Z","title":"Towards understanding the generative capability of adversarially robust classifiers,","venue":null,"work_id":"4a47ebfb-c734-4e5f-a737-1dac034fc99a","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.114402Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f58ffa9968d90bbf8a131877d70fe0a30f43e7ce773a15e744a65af58e44a78a","observation_id":"e26de8b8-836b-42b0-982a-43de417b4992","resolution":{"observed_at":"2026-08-07T13:13:12.269904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:11.863867Z","title":"Your classifier is secretly an energy based model and you should treat it like one,","venue":null,"work_id":"5df780b3-8d6e-4635-aaad-1a2358cdd430","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.256012Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:a08473d5298e29b97cda2206908162b7326bcee75c8b47f6606655b7f19eef6d","observation_id":"e2d7bf46-7cc0-4b33-a6e6-6346d9762a46","resolution":{"observed_at":"2026-08-07T13:13:11.984573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:11.640520Z","title":"Exploring the connection between robust and generative models,","venue":null,"work_id":"3a51c68b-f6eb-4a21-ba9e-32c5fc93e328","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.361288Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:1b3366245c7edcc451eb184aed2af98a04bbc194d518d1bb0ee1b9b7715a5d8f","observation_id":"60218606-f761-4548-961c-901edfe2f03d","resolution":{"observed_at":"2026-08-07T13:13:11.726242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:12:57.502317Z","title":"Towards evaluating the robustness of neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.502317Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:22d5933def319ed265a87860bddc03a34cbaf61bc77f837a280683c6eb374b0c","observation_id":"6a0e3bad-1807-4593-bf0f-41b341a90dee","resolution":{"observed_at":"2026-08-07T13:12:57.502317Z","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":"2026-08-07T13:12:57.629828Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.629828Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:a689d738a6f33aa39d25328bde5d32d77a30e1fffd9d5757af069bedbd29739a","observation_id":"72dcc6ad-8547-408a-a9c2-1af44e4809ab","resolution":{"observed_at":"2026-08-07T13:12:57.629828Z","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":"2026-08-07T13:13:11.394777Z","title":"Diffusion-based adversarial sample generation for improved stealthiness and controllability,","venue":null,"work_id":"a2e06e1c-265e-42c0-95c0-d1215de42712","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.787913Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:213fc9ab4007155c95a55767c58dd31f6bacaf0cb9ba5dc995cec92fafab2e33","observation_id":"b14208c6-d970-4dd9-99bc-eee238087208","resolution":{"observed_at":"2026-08-07T13:13:11.510203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.06373","last_updated":"2018-03-16T19:03:45Z","snapshot_observed_at":"2026-07-06T06:28:44.644165Z","submitted_at":"2018-03-16T19:03:45Z","title":"Adversarial Logit Pairing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.06373","snapshot_observed_at":"2026-08-07T13:12:57.863828Z","title":"Adversarial logit pairing,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.863828Z"},"links":{"cited_paper":"/paper/1803.06373","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:e851e75aebce4002e9b761e076f710214b731fe08d2864c7a1bef97a4d170da1","observation_id":"ed4902c9-d270-4172-954d-1f1d08ee2160","resolution":{"observed_at":"2026-08-07T13:12:57.863828Z","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":"2026-08-07T13:13:11.072344Z","title":"Eliminating catastrophic overfitting via abnormal adversarial examples regularization,","venue":null,"work_id":"0465e4ae-5316-4ee8-b476-e63a7ba46b6a","year":2024},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:57.962795Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:d284a5a1c2fad528707fe8d5c2ebe6e97234c3a3ff315b783eec2aad43ec37d6","observation_id":"bfb73959-80ea-49f5-a598-9685c9f8d293","resolution":{"observed_at":"2026-08-07T13:13:11.258453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:10.823016Z","title":"On adversarial training without perturbing all examples,","venue":null,"work_id":"a2d106d3-d373-488c-9b78-17df81c9d0da","year":2024},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.038432Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:2881a80578897b7adc96621e34387ba4e8e64b9feb6eed616f4393d71a9d7890","observation_id":"b1be3814-4cfe-498e-b83e-5b5b47414740","resolution":{"observed_at":"2026-08-07T13:13:10.954297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:10.565793Z","title":"On the over-memorization during natural, robust and catastrophic overfitting,","venue":null,"work_id":"ede4990f-8b88-44d8-b1df-ca5a4a29a4fd","year":2024},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.093602Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:8f8859af8a26b8af934e9181b4575be57ff8baa3457265961525be60b30ff226","observation_id":"bfaa7bdb-ecfc-471f-b46a-6ee2e394e008","resolution":{"observed_at":"2026-08-07T13:13:10.696753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:10.302194Z","title":"Square attack: a query-efficient black-box adversarial attack via random search,","venue":null,"work_id":"1ad07e07-7c9f-4e7a-bd67-d59e911fb547","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.216400Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:fc076c62a6f185f94849ededea9ff89e1c554f94ef5b490d877ee6e1eb54df40","observation_id":"0c8fa87a-50d3-4484-8a14-d16497a0c0d1","resolution":{"observed_at":"2026-08-07T13:13:10.425179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13948","last_updated":"2024-10-27T08:32:11Z","snapshot_observed_at":"2026-08-06T16:12:42.070710Z","submitted_at":"2023-05-23T11:17:45Z","title":"Decoupled Kullback-Leibler Divergence Loss","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13948","snapshot_observed_at":"2026-08-07T13:12:58.304197Z","title":"Decou- pled kullback-leibler divergence loss,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.304197Z"},"links":{"cited_paper":"/paper/2305.13948","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:5d3ac75b1bf2675aca52aa1ad23d0cad8b7cacffa42179597e3db888ec28120b","observation_id":"dac37fe8-b8a6-4c8b-ac4b-15a6c40c3163","resolution":{"observed_at":"2026-08-07T13:12:58.304197Z","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":"2026-08-07T13:13:09.925924Z","title":"Ensemble adversarial training: Attacks and defenses,","venue":null,"work_id":"774c47b0-ed13-4a05-8431-bb32c07d0c99","year":2018},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.380389Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:40cf93f012f0880ce829cc1ad3238a315fa4c5944d59ec28e36ad19851f98a52","observation_id":"e866b9ba-b3fb-4c7d-852e-215453f0a06e","resolution":{"observed_at":"2026-08-07T13:13:10.062470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:09.656752Z","title":"Single-step adversarial training with dropout scheduling,","venue":null,"work_id":"18f4863a-ed34-4f0b-b74c-2c33ab9bd7ed","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.486692Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f3667f962221b545368f61f92301c3b331d5a340a631bc49dda3eab130c62812","observation_id":"0bc130ad-c6a9-41f1-b17f-5bd13100b750","resolution":{"observed_at":"2026-08-07T13:13:09.792398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:09.340792Z","title":"Make some noise: Reliable and efficient single-step adversarial training,","venue":null,"work_id":"b770a184-125a-4af2-9614-780028e74445","year":2022},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.600999Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:97443e44ef033ea9ee5523a247c7cd6ab31a2fae71c03746ea7d5c84efb40ac0","observation_id":"e248ae70-0226-4ddf-a26e-b13ef1a83b52","resolution":{"observed_at":"2026-08-07T13:13:09.519475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:09.075916Z","title":"Reliably fast adversarial training via latent adversarial perturbation,","venue":null,"work_id":"83a719d4-d783-4dae-84f3-1987820b78b3","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.710490Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f4b2503a8eb9af12f133919b27506690ca50cb180ab5f27023e5c6fca74c0cf2","observation_id":"6f98ffbd-4f4e-4efa-9caf-83400634bfc8","resolution":{"observed_at":"2026-08-07T13:13:09.204188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:08.810764Z","title":"Zerograd: Costless conscious remedies for catastrophic overfitting in the fgsm adversarial training,","venue":null,"work_id":"e719b639-8b6d-44d7-a5cb-12649e024751","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.777380Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:7484d784d1727644beeee6726f96ecb88153f036a8a5ea6891eeabc4bb86ed6f","observation_id":"fdd432a1-1306-4182-bce8-d1d266f31bd2","resolution":{"observed_at":"2026-08-07T13:13:08.939792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:08.563932Z","title":"Understanding and improving fast adversarial training,","venue":null,"work_id":"7c534ba1-f266-4289-8654-73dee60e7937","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:58.906417Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:b578ca0bdab847e07100c0f07d43f16642c8d3f3ec1a3670d0c768f05c89fe05","observation_id":"0fb15b3e-ac9a-4cc5-9211-ce8398a43d42","resolution":{"observed_at":"2026-08-07T13:13:08.669194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:08.429017Z","title":"Subspace adversarial training,","venue":null,"work_id":"5032ca51-c464-4af8-ac38-fdb53ba948d0","year":2022},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.006545Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:b604bb703cdc929ff936b5606e1f21ade31fef6321d6ec4a4a456d623a0c242d","observation_id":"124cb047-a8e3-4156-af27-67e85c6144fa","resolution":{"observed_at":"2026-08-07T13:13:08.496282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:08.286559Z","title":"Fast adversarial training with adaptive step size,","venue":null,"work_id":"56e393f3-8457-49d2-9697-c61479b76c2f","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.085856Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:b039ef26d067e97346c207187ebcf2dd0a2e801e9222b6ca85917428ad780b55","observation_id":"bd1fea41-ba9e-4e75-866a-c4781329fc8e","resolution":{"observed_at":"2026-08-07T13:13:08.357499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:08.079107Z","title":"Adver- sarially robust generalization requires more data,","venue":null,"work_id":"c4f84cd6-947f-461b-b3e1-56cc915661ac","year":2018},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.183849Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:6f55d90edfe4db18111a33a020d1b1760b199e70543f0b1f1c799ee3a0fbb571","observation_id":"113d1ea3-273f-44d6-ac1d-2a65740f0c1b","resolution":{"observed_at":"2026-08-07T13:13:08.217177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:07.957750Z","title":"Are labels required for improving adversarial robustness?","venue":null,"work_id":"f7321d8c-1052-435b-931a-4a5e9b18bb13","year":2019},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.279241Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:224c4fa42d4e6f61fe537bb9f875a36a07af4226ed072c9bf12d73d5c6ebdc13","observation_id":"4b481688-23fa-4347-9aa2-88faf51f4041","resolution":{"observed_at":"2026-08-07T13:13:08.001454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.00555","last_updated":"2019-09-26T01:44:46Z","snapshot_observed_at":"2026-07-06T07:57:23.973409Z","submitted_at":"2019-06-03T03:56:41Z","title":"Adversarially Robust Generalization Just Requires More Unlabeled Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.00555","snapshot_observed_at":"2026-08-07T13:12:59.355379Z","title":"Adversarially robust generalization just requires more unlabeled data,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.355379Z"},"links":{"cited_paper":"/paper/1906.00555","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:53ed68d017e00a36c2660a6f613c010fbdf6de7f2c510ee1a0f409d072e81a83","observation_id":"c7ece742-dbc1-4ffb-896e-423c6a1d4d79","resolution":{"observed_at":"2026-08-07T13:12:59.355379Z","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":"2026-08-07T13:12:59.474651Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.474651Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:4add5decdd586bb6528f9bd76ff0d2271f1e11fade9a99780e906990d2648a4f","observation_id":"30a4b299-e2f6-42bb-8f8f-5f5bb1174ae9","resolution":{"observed_at":"2026-08-07T13:12:59.474651Z","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":"2026-08-07T13:13:07.945512Z","title":"Exploring memorization in adversarial training,","venue":null,"work_id":"c4b16116-d967-447f-be99-51d82c1c9d21","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.553489Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:89204a806fbcce9924c2c009bb328f07b1dd3482ec90370f698bf037167a888e","observation_id":"a15e0164-c52c-43f8-91b5-3313ba31e5d3","resolution":{"observed_at":"2026-08-07T13:13:07.948569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:07.756198Z","title":"Enhancing adversarial training via reweighting optimization trajectory,","venue":null,"work_id":"d5f6f6c6-071d-4c45-a493-1e77c21b95dd","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.617659Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:c1e0cc028a3027282af6c85205038726a83a5fa2332a6a58294bb2368e2f5862","observation_id":"aa82b3b7-6a95-446c-a95c-e335ba2a3837","resolution":{"observed_at":"2026-08-07T13:13:07.859581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.09844","last_updated":"2022-02-27T07:42:30Z","snapshot_observed_at":"2026-08-02T09:05:26.776973Z","submitted_at":"2022-02-20T15:52:08Z","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.09844","snapshot_observed_at":"2026-08-07T13:12:59.672324Z","title":"Sparsity winning twice: Better robust generaliztion from more efficient training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.672324Z"},"links":{"cited_paper":"/paper/2202.09844","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:e5f6d3e42467bc6920200d75226ab1f31f8761ea0864128c63400ffd1f8b7482","observation_id":"8ce0a46a-f246-49b5-8b15-3ab9c510bcb5","resolution":{"observed_at":"2026-08-07T13:12:59.672324Z","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":"2026-08-07T13:13:07.549406Z","title":"Relating adversarially robust generalization to flat minima,","venue":null,"work_id":"abb0d736-be23-42a2-ab8e-7e85ad883624","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.738598Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:19bc5717bda724002d02bcadb30959ebcd79e57eec1e156cc592b6533722dade","observation_id":"74f326ab-cbd0-43d0-857e-3d8afde765f8","resolution":{"observed_at":"2026-08-07T13:13:07.656530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:07.320379Z","title":"Low curvature activations reduce overfitting in adversarial training,","venue":null,"work_id":"8881ea0f-d0de-4006-b988-ddc6dfa1e887","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.817351Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:7e6ff7f6e587b8fd14a62c5cfce62a2cfb792b12efca6ff95a28ef33346a7e31","observation_id":"3ccdfd84-cba8-4c6f-973f-f722abaa5546","resolution":{"observed_at":"2026-08-07T13:13:07.449253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:07.014967Z","title":"Robust overfitting may be mitigated by properly learned smoothening,","venue":null,"work_id":"4d46eac6-a5a6-4af4-8b16-cc27c33f1ba4","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:12:59.908858Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:2671a20912de3aeb86765a67fd3b4297956a4e0ec77de0cb46e18819a74fc380","observation_id":"b9e4f7f6-59d9-49da-9cf3-45e858dcbee5","resolution":{"observed_at":"2026-08-07T13:13:07.177038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:06.752034Z","title":"Adversarial robustness through the lens of causality,","venue":null,"work_id":"88f056b0-fce0-4453-9959-179447efa2e6","year":2022},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.012758Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:82ceba7c8048667e08571c85f5a1545bbdd2d4a62d7cad584ff685bb9eaf37d8","observation_id":"bdd7c572-e147-4396-954c-98cfc86cabb8","resolution":{"observed_at":"2026-08-07T13:13:06.897365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:06.572128Z","title":"Understanding robust overfitting of adversarial training and beyond,","venue":null,"work_id":"da390877-04c9-4c0b-aa6a-595002122d2a","year":2022},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.093363Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:0eb36feb5fa4600a1a1e96801c30b9ca6bd2c4a1a61501795a7d6cd963b5f5c7","observation_id":"5e94165f-4856-4274-b736-2d68e146d783","resolution":{"observed_at":"2026-08-07T13:13:06.643160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:06.389588Z","title":"Jem++: Improved techniques for training jem,","venue":null,"work_id":"11108db1-a5ee-445f-bc64-da1ffa131efa","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.161578Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:9aec60b2e3371ace02c5cbbe5a68a261db0d269a4273b19c397a246074750941","observation_id":"ce625ceb-4b40-4b4f-8d6e-d9d16fdae200","resolution":{"observed_at":"2026-08-07T13:13:06.484127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:06.156545Z","title":"Sharpness-aware minimization for efficiently improving generalization,","venue":null,"work_id":"f6439eb3-c2b9-4c74-9280-9ad5b67973cf","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.223723Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:1cc6a79c57c78f24ce5bd47fedc3c0c4563e8ecaf0f2198b88008b29c40f6fb6","observation_id":"2b4e48af-f395-4764-ac75-8ab02ea28211","resolution":{"observed_at":"2026-08-07T13:13:06.312041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:05.950452Z","title":"A unified contrastive energy- based model for understanding the generative ability of adversarial training,","venue":null,"work_id":"6266922e-fc03-4c26-bc2f-e70cc3323e57","year":2022},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.311281Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:c1045d07c15985df9a853e2e3d23ec181d278dfea5f1f9a41a4f37be766fc146","observation_id":"889c1e7a-1aed-4e46-873d-cd95ac63ddf8","resolution":{"observed_at":"2026-08-07T13:13:06.040436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:05.822809Z","title":"Towards bridging the performance gaps of joint energy-based models,","venue":null,"work_id":"5f2936de-9b5f-43b2-9eb2-705471bd8e63","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.415153Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:fbdd61d46bc53fa1a2a2c51063f9bc0a439c05afe364ee56d52281b834e1f471","observation_id":"4bdb9030-b2e2-4710-843b-abc0e6c6a13f","resolution":{"observed_at":"2026-08-07T13:13:05.872021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:05.698926Z","title":"M-ebm: Towards understanding the manifolds of energy-based models,","venue":null,"work_id":"ac8a1421-b123-49c1-95b2-3dd5f353dcd0","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.512632Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:5031d5d037c5b69d1ea4646cc145c8b8c97e692a287294688bed83fa538eea49","observation_id":"719aa396-7645-4929-9bf6-2b5fbf10b9ed","resolution":{"observed_at":"2026-08-07T13:13:05.755245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.06927","last_updated":"2022-10-21T17:59:55Z","snapshot_observed_at":"2026-07-06T11:18:44.145746Z","submitted_at":"2021-06-13T05:51:00Z","title":"Inverting Adversarially Robust Networks for Image Synthesis","version":5},"cited_work":{"arxiv_id":"2106.06927","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.06927","snapshot_observed_at":"2026-08-07T13:13:02.773798Z","title":"Inverting Adversarially Robust Networks for Image Synthesis","venue":"cs.CV","work_id":"476a347c-c69c-43e5-b37e-6e2d3f614b69","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.580715Z"},"links":{"cited_paper":"/paper/2106.06927","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:506fb71f673683f53addf5f16b917e6e643c9c84a0886b343313222930b5f2c8","observation_id":"b4d90ab8-cc2f-4d2a-b9fd-75fecf2ec325","resolution":{"observed_at":"2026-08-07T13:13:02.879218Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:05.520381Z","title":"MAGIC: Mask-guided image synthesis by inverting a quasi-robust classifier,","venue":null,"work_id":"cc6bb09d-65f2-40c6-8478-c45295431641","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.678402Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:d048c1219a92d7f2b5befb68f3dca21f2f4dce1beb83988e90428a5a25d89fac","observation_id":"af46d98a-33cc-4e6a-830b-583d9bab7405","resolution":{"observed_at":"2026-08-07T13:13:05.619350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:05.322798Z","title":"Effective single-step adversarial training with energy-based models,","venue":null,"work_id":"6763aa61-cb56-4f5d-98b6-5336588c045b","year":2024},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.752435Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:98c9947af34b16b2055c444cf41f18c7ce6d72590eda8bf8efabea4a64802fcf","observation_id":"322ec248-6ff7-4b0f-8923-291059f0703b","resolution":{"observed_at":"2026-08-07T13:13:05.427053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:05.136679Z","title":"Geometry-aware instance-reweighted adversarial training,","venue":null,"work_id":"ee672b28-b350-413c-8bd9-59a61620c597","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.844589Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f5b9e06f87a63803c9b99078b9a85b0fea70c0b13708fde0b0536dda2edb2631","observation_id":"767a039d-8571-4d85-acc9-1068b96f2a33","resolution":{"observed_at":"2026-08-07T13:13:05.232405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.01914","last_updated":"2021-03-05T13:04:35Z","snapshot_observed_at":"2026-07-06T10:46:11.856932Z","submitted_at":"2021-03-02T18:15:42Z","title":"Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial Training","version":2},"cited_work":{"arxiv_id":"2103.01914","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.01914","snapshot_observed_at":"2026-08-07T13:13:02.533835Z","title":"Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial Training","venue":"cs.LG","work_id":"0cf03fe4-bcfd-4b60-978e-7019d6ee40d8","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:00.930617Z"},"links":{"cited_paper":"/paper/2103.01914","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f86be5d1fea0b500419dc44705d44184590399992a11b71f1610f2aeb1d1caae","observation_id":"41a057b5-d254-4099-b731-3461a6e22089","resolution":{"observed_at":"2026-08-07T13:13:02.639233Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:04.874256Z","title":"Entropy weighted adversarial training,","venue":null,"work_id":"5e4fd2bf-9f65-4eaf-932f-a0fd46ff8be7","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.035151Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:8fe72fb147c1c9b50798edde7222f645dc8fceb94c7fb1f44a8383aa63202b31","observation_id":"eb2ee494-0d44-47da-95ca-252242ccc880","resolution":{"observed_at":"2026-08-07T13:13:05.009419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:04.690261Z","title":"Memorization weights for instance reweighting in adversarial training,","venue":null,"work_id":"aaec8724-512a-48c1-8d8e-2b733352244a","year":2023},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.118223Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:04dae7ac61b84a58f1fbd9cde7c7c5822cb5fabe281508093c003e60c9d6f32a","observation_id":"1189317d-a055-475f-b691-f5cfafd2c587","resolution":{"observed_at":"2026-08-07T13:13:04.787059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:04.500719Z","title":"A tutorial on energy-based learning,","venue":null,"work_id":"da869ff9-2ca0-4535-9ddc-9afe85e61d8b","year":2006},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.232411Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:3f1ed2b7d3e506bdca9c305bdf8c22464ddaa5a8751b43db4c14be37435b6edb","observation_id":"e9ce07d8-cb7f-47d8-bb85-83d8ee262c63","resolution":{"observed_at":"2026-08-07T13:13:04.575435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:04.358944Z","title":"Generative modeling by estimating gradients of the data distribution,","venue":null,"work_id":"739bee42-2b2b-4884-b059-684a7c8110c7","year":2019},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.308222Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:390ca8c1b75dde496fba6b7d56b851c7f78063118c34d37a3b594aa345e4a3a4","observation_id":"3436c544-cede-4f1b-898a-cbdcd73bce69","resolution":{"observed_at":"2026-08-07T13:13:04.428961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:01.354256Z","title":"Diffusion models beat gans on image synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.354256Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:302f45fd3de6b42cbb8b3c0b0d06954c3bdb20f24f39dcc738ab95e5a57bbdbd","observation_id":"0de7f175-416b-4555-b065-d266c844ebf6","resolution":{"observed_at":"2026-08-07T13:13:01.354256Z","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":"2026-08-07T13:13:04.202675Z","title":"Attacks which do not kill training make adversarial learning stronger,","venue":null,"work_id":"d3266ff2-6087-4d1d-b9d9-20ca5bd61485","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.451104Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:b935594779f68fd05d09de69cdd60306f8e16700e9b9935f7e4d5f3fea75f50e","observation_id":"2a1864bf-7903-4c6b-b78c-9f8bc8fb2ae6","resolution":{"observed_at":"2026-08-07T13:13:04.264883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:04.053186Z","title":"Mma training: Direct input space margin maximization through adversarial training,","venue":null,"work_id":"02a2ab9b-3364-4657-a35d-366f36b371c2","year":2020},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.561699Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:82875b2d6b54751d12d5fec7270f515b3ed1f17cf685dded21f3bf51e1af966b","observation_id":"831a71f1-e537-45f5-b9f0-3448329bfe00","resolution":{"observed_at":"2026-08-07T13:13:04.100110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:01.657710Z","title":"Image quality assess- ment: From error visibility to structural similarity,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.657710Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:4e2f27f89b31247d88920d60d0ed3869788294f0bd80afe4f9cf8929fc158777","observation_id":"16e87bc9-8b7c-4299-abe2-eb592437c6e9","resolution":{"observed_at":"2026-08-07T13:13:01.657710Z","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":"2026-08-07T13:13:01.760123Z","title":"Improved techniques for training gans,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.760123Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:886ef8d766711c999546517504f78707c3cad87edd058dc36435788c900f7fb2","observation_id":"d4165823-f335-4db1-ae97-095c5c612511","resolution":{"observed_at":"2026-08-07T13:13:01.760123Z","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":"2026-08-07T13:13:03.824935Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium,","venue":null,"work_id":"99aeb8d1-5013-461b-a291-59a3d361a7c5","year":2017},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.822836Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:7375acb076abf601d5eaef1888cb322284ed2d820d782acc67f4703273f0a895","observation_id":"c0864371-e77e-4991-8cae-01e698fc0684","resolution":{"observed_at":"2026-08-07T13:13:03.930878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:03.657858Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"5813953a-db1c-477c-81ef-15e187cee8ad","year":2009},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:01.939701Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:bf7712232ee2eed805765322aa6a5e0920a6721a5660c6ffa41783da18b86599","observation_id":"c694b63b-88e8-49fa-adbf-6e6d2bb1d3a2","resolution":{"observed_at":"2026-08-07T13:13:03.743157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:03.507567Z","title":"Reading digits in natural images with unsupervised feature learning,","venue":null,"work_id":"37ea433f-1f57-427a-b40e-2ecfb3792bef","year":2011},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:02.040506Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:efde6e5489499a2365fcc07bf998f8854d62140f31d425e19483aabbe6c3735c","observation_id":"2563dbb0-9857-4499-9ff9-1ad999610590","resolution":{"observed_at":"2026-08-07T13:13:03.576933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:03.339156Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":"e5335077-19fa-42de-b8a1-566740ce0bab","year":2009},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:02.144640Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:b99e721fa15f2ba66c7c21dd763eff3eed6ccc1027c88c721f203d1bb938c660","observation_id":"c0841b46-25fe-407d-812d-59a54e72fb51","resolution":{"observed_at":"2026-08-07T13:13:03.390052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05407","last_updated":"2019-02-25T14:18:11Z","snapshot_observed_at":"2026-07-31T19:09:21.589864Z","submitted_at":"2018-03-14T17:09:27Z","title":"Averaging Weights Leads to Wider Optima and Better Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05407","snapshot_observed_at":"2026-08-07T13:13:02.224237Z","title":"Averaging weights leads to wider optima and better generalization,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:02.224237Z"},"links":{"cited_paper":"/paper/1803.05407","citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:ade5c7a68ec231a997302d442394743388cea28bc3decfd044caa8f8d05a8055","observation_id":"14f12785-9ec6-4575-abfc-89ba73b746c5","resolution":{"observed_at":"2026-08-07T13:13:02.224237Z","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":"2026-08-07T13:13:03.147985Z","title":"Learning energy-based models by diffusion recovery likelihood,","venue":null,"work_id":"ef3e9406-8115-4a70-82de-1daf9113a2bc","year":2021},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:02.317664Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:f2f3435a2876363ccb695974d5eb68d42c10cac3ad719c05a84140886adabf3b","observation_id":"5f22cb8f-8676-40b3-b2cb-3a2e4f7d30d6","resolution":{"observed_at":"2026-08-07T13:13:03.217551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:13:02.995854Z","title":"Image synthesis with a single (robust) classifier,","venue":null,"work_id":"ad272766-4673-4ada-87cc-475c79aba4f5","year":2019},"citing_paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:02.411975Z"},"links":{"citing_paper":"/paper/2505.22486"},"observation_digest":"sha256:a3bd7d1593580c187b0e57fe93a67f113cab667e0b9648f3a68f0f52c39c974a","observation_id":"d8b2339d-663e-49b3-90e2-2e0c4211a1e9","resolution":{"observed_at":"2026-08-07T13:13:03.059743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.22486","last_updated":"2025-05-28T15:36:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T13:03:37.618640Z","submitted_at":"2025-05-28T15:36:02Z","title":"Understanding Adversarial Training with Energy-based Models"},"reference_resolution":{"displayed":77,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":2,"verified_fuzzy":63},"total_outbound_references":77},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 0 inbound Pith citation observations for arXiv:2505.22486."}