{"as_of":"2026-08-09T20:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ad516b9343551eb9258cc3cd20eebdc0c6bd71aa00da3159c5c8e854b0c83108","coverage":[{"denominator":17,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T23:07:31.266899Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T00:39:43.196010Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T00:39:48.128864Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"cited_work":{"arxiv_id":"2502.04248","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04248","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adapting to evolving adversaries with regularized continual robust training","venue":null,"work_id":"6e3c8579-6fc2-42cc-b729-5b9b92fa88b2","year":2025},"citing_paper":{"arxiv_id":"2604.20704","last_updated":"2026-04-22T15:46:11Z","snapshot_observed_at":"2026-07-06T23:07:25.185196Z","submitted_at":"2026-04-22T15:46:11Z","title":"Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T00:39:43.196010Z"},"links":{"cited_paper":"/paper/2502.04248","citing_paper":"/paper/2604.20704"},"observation_digest":"sha256:9f35bbba9780a518e7be04dd41e9475e2170e75759435089ac868ac185c82099","observation_id":"cb3e4588-8047-49fa-9af0-abf36eeae24b","resolution":{"observed_at":"2026-05-10T00:39:48.131345Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.04248/citation-record","integrity":"/paper/2502.04248/integrity","json":"/paper/2502.04248/citation-record.json","paper":"/paper/2502.04248"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T23:07:31.500626Z","title":null,"venue":null,"work_id":"41f068e8-8bea-4464-92a8-0a6e8bec9424","year":null},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.245497Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:ceef318ce97c3a3c180eeda3a04ec7e48d5724973360791c5f0351477e992996","observation_id":"7fbd3025-b74f-4b5a-bf90-7b57b7532b69","resolution":{"observed_at":"2026-08-08T23:07:31.503737Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T23:07:31.492729Z","title":null,"venue":null,"work_id":"85a88a21-aa7c-40b6-88f2-03c0100cb829","year":null},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.248574Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:c6c72369b3240389e13d7d35e094db5992d45a7d73a2b5e706954eb3bd9f5cfd","observation_id":"953c78e0-aa45-4c5e-a293-72dd9a165aaa","resolution":{"observed_at":"2026-08-08T23:07:31.495618Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T23:07:31.483643Z","title":null,"venue":null,"work_id":"bcde7ece-1972-400c-8a8d-b5cae7bf5a45","year":null},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.251599Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:adae5948b5dea0257dbd78a172d07aafb2b35c96bb80ff95a65489ca46e7d97c","observation_id":"16c31f60-b46c-4555-a721-4f955269bf72","resolution":{"observed_at":"2026-08-08T23:07:31.487326Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-08T23:07:31.227870Z","title":"ISBN 978-1-939133-37-3","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.227870Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:22299211fa447b2001ac2eec68ff8cdf3188d4178c461f78a53f013c2c206e53","observation_id":"deb37944-da27-40c4-a917-8c9558a510f9","resolution":{"observed_at":"2026-08-08T23:07:31.227870Z","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":"2026-08-08T23:07:31.467074Z","title":null,"venue":null,"work_id":"850361ee-cda4-4fa2-a2bd-825e2b486880","year":null},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.257934Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:a12d4fa9d8265ffef176db85d3186d1a5538fccef3ab12a9e377e9fee68eeceb","observation_id":"e8aa49f4-5abd-4c4a-a59b-02beb245cff3","resolution":{"observed_at":"2026-08-08T23:07:31.470018Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T23:07:31.458477Z","title":"Additional Related Work Adversarial Attacks and Defenses: ML models are vulnerable to input-space perturbations known as adversarial examples (Szegedy et al., 2014)","venue":null,"work_id":"69d5c156-32f1-49fc-a70a-7522da2f6f4f","year":2014},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.260812Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:b58f150378e04913f590222bc39f80791b8c7c9a459f74beee3920f48c1db2b3","observation_id":"0f32566d-595a-4ea6-9895-267c9ba8a7d0","resolution":{"observed_at":"2026-08-08T23:07:31.461632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T23:07:31.382871Z","title":"URL http: //openaccess.thecvf.com/content_cvpr_ 2018/html/Zhang_The_Unreasonable_ Effectiveness_CVPR_2018_paper.html","venue":null,"work_id":"5f91659b-9435-45eb-9292-6036376bd8bf","year":2018},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.242467Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:1c019aaf746e1a417bd709c4f377f95685055bf24fe27374c8d89fc45f9d46bd","observation_id":"bd50f0ea-f63b-4879-b495-e3ce9dbc8957","resolution":{"observed_at":"2026-08-08T23:07:31.386716Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T23:07:31.475237Z","title":null,"venue":null,"work_id":"f1f10313-5df1-43f8-a1a7-29dfbf215633","year":null},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.254886Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:2c985c1820ddbecf75d005727f4f4cc82110c6a4661240cea559c60c886ecb12","observation_id":"abf67717-c5c1-48f1-8a2e-709cd9bdaeae","resolution":{"observed_at":"2026-08-08T23:07:31.478126Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04286","last_updated":"2020-09-22T22:53:45Z","snapshot_observed_at":"2026-07-06T09:03:25.467987Z","submitted_at":"2020-03-09T17:45:44Z","title":"Manifold Regularization for Locally Stable Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2003.04286","doi":null,"metadata_source":"pith","pith_arxiv_id":"2003.04286","snapshot_observed_at":"2026-08-08T23:07:31.416110Z","title":"Manifold Regularization for Locally Stable Deep Neural Networks","venue":"stat.ML","work_id":"7d1dc960-8ffd-4a5c-ab40-2c75bbd0756a","year":2020},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.223455Z"},"links":{"cited_paper":"/paper/2003.04286","citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:0919a92fb292e0172675fa3191b7e8e8889999b09492b562ff38594cf22ccbb9","observation_id":"02787b62-0ebb-4621-929c-36344fcc897e","resolution":{"observed_at":"2026-08-08T23:07:31.419451Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T23:07:31.620308Z","title":"Zhang, H., Yu, Y ., Jiao, J., Xing, E","venue":null,"work_id":"4b0ff4f0-cce4-4168-b8ae-b02229768dab","year":2016},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.236112Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:b02fc1f0a15c6fbf4ba19827e86af8d7e6cf9c010abc5f4d28de5117c567aff8","observation_id":"6051aa7e-e847-4f71-a586-aaf9e4e7c816","resolution":{"observed_at":"2026-08-08T23:07:31.623262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10430","last_updated":"2025-04-28T15:25:39Z","snapshot_observed_at":"2026-07-06T15:05:12.470716Z","submitted_at":"2023-03-18T14:54:57Z","title":"NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models","version":2},"cited_work":{"arxiv_id":"2303.10430","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.10430","snapshot_observed_at":"2026-08-08T23:07:31.395126Z","title":"NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models","venue":"cs.LG","work_id":"fa24b4a6-f5f2-4dd5-8fb1-fa62076af755","year":2023},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.231691Z"},"links":{"cited_paper":"/paper/2303.10430","citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:b44d33b5f8d8dd42c72253fe6fe7d3a70dfe9c44f60d62bbc82cfbbf6c3f75c8","observation_id":"18e5eea0-39c5-410b-a202-0f19393d33fe","resolution":{"observed_at":"2026-08-08T23:07:31.399074Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.09670","last_updated":"2021-10-31T20:03:39Z","snapshot_observed_at":"2026-08-09T09:16:24.377074Z","submitted_at":"2020-10-19T17:06:18Z","title":"RobustBench: a standardized adversarial robustness benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.09670","snapshot_observed_at":"2026-08-08T23:07:31.211913Z","title":"Croce, F","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.211913Z"},"links":{"cited_paper":"/paper/2010.09670","citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:2683db1f8099fc641779d0ce5637298f779443ae8698cc20c85ae28a2c2a7ac1","observation_id":"475c79f6-5f24-4a9a-9b33-9d4f5b94e030","resolution":{"observed_at":"2026-08-08T23:07:31.211913Z","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":"2026-08-08T23:07:31.449981Z","title":null,"venue":null,"work_id":"3d62dc60-7b67-4401-a25e-3545c29c967e","year":null},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.263750Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:387fdc452854890110ebee0cb5f899acc6f923976e5647dd36e286dcf7a4d412","observation_id":"8d9582d9-9974-4e46-8ed0-c4d4f592c727","resolution":{"observed_at":"2026-08-08T23:07:31.452936Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T23:07:31.441155Z","title":"+ ALR feature","venue":null,"work_id":"b7877608-9678-40bd-aa65-54dc1d89ca2d","year":2020},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.266899Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:de30da0fd3123b736f3735b7ec9b2b1a59bf8ededccf248a88035be1344b5871","observation_id":"b9d4c0e6-2dd6-47b7-875b-9901b7377380","resolution":{"observed_at":"2026-08-08T23:07:31.444508Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.01349","last_updated":"2024-10-08T15:56:45Z","snapshot_observed_at":"2026-08-04T08:19:12.400686Z","submitted_at":"2024-05-02T14:58:44Z","title":"Position: Towards Resilience Against Adversarial Examples","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.01349","snapshot_observed_at":"2026-08-08T23:07:31.216225Z","title":"Dai, S., Ding, W., Bhagoji, A","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.216225Z"},"links":{"cited_paper":"/paper/2405.01349","citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:f8aa1e2a6500dda69c45ff6ee1d17be2bd24f1b192b8f25e32bf28e21e142b1a","observation_id":"d20ebdfd-7980-4c5a-a96e-ef9b6b4507b9","resolution":{"observed_at":"2026-08-08T23:07:31.216225Z","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":"2026-08-08T23:07:31.611814Z","title":"URL http://proceedings","venue":null,"work_id":"8a1d6497-666d-4a6e-8799-e7eca8abde19","year":2019},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":7482,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.239568Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:7f580b1eaf8a428a72707cf6209a0a190a9be3fabb083e605dd171bf051d58f5","observation_id":"eb5b9db8-986a-4f79-aece-4fde85ae624a","resolution":{"observed_at":"2026-08-08T23:07:31.615087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.patrec.2021.03","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T23:07:31.294408Z","title":null,"venue":null,"work_id":"25a05e16-2037-4554-87fd-9072b18937a9","year":2021},"citing_paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training","version":1},"reference_index":8655,"source":"pdf_text","source_observed_at":"2026-08-08T23:07:31.219947Z"},"links":{"citing_paper":"/paper/2502.04248"},"observation_digest":"sha256:7c7d7be576efed90bf9038a289aaea036253e9331b2e5105a41eed6d79c9e296","observation_id":"d275753b-7e7a-4732-9e20-1838a7d7608d","resolution":{"observed_at":"2026-08-08T23:07:31.298583Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.04248","last_updated":"2025-02-06T17:38:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T09:17:12.044635Z","submitted_at":"2025-02-06T17:38:41Z","title":"Adapting to Evolving Adversaries with Regularized Continual Robust Training"},"reference_resolution":{"displayed":17,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":9,"verified_exact":3,"verified_fuzzy":3},"total_outbound_references":17},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 1 inbound Pith citation observation for arXiv:2502.04248."}