{"as_of":"2026-08-09T19:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8859af6a36e4e357d707e307f7e3b57c88be97083bb26703d5ed235416f6f7a8","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:40:55.076997Z","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":"2026-07-03T21:18:59.597420Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.09425","last_updated":"2022-03-03T15:38:12Z","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09425","snapshot_observed_at":"2026-08-09T17:40:55.076997Z","title":"Robust learning meets genera- tive models: Can proxy distributions improve adversarial robustness? arXiv preprint arXiv:2104.09425,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00834","last_updated":"2025-02-02T16:15:10Z","snapshot_observed_at":"2026-08-09T17:30:15.615166Z","submitted_at":"2025-02-02T16:15:10Z","title":"Boosting Adversarial Robustness and Generalization with Structural Prior","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T17:40:55.076997Z"},"links":{"cited_paper":"/paper/2104.09425","citing_paper":"/paper/2502.00834"},"observation_digest":"sha256:9227a0aa6c22cb2dc7cae07ba5fd87000db35709216f8ab7bac47577224425e7","observation_id":"43bc05a8-298d-40cd-b89d-165fb95c561a","resolution":{"observed_at":"2026-08-09T17:40:55.076997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09425","last_updated":"2022-03-03T15:38:12Z","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09425","snapshot_observed_at":"2026-08-07T05:12:28.373700Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.08611","last_updated":"2025-06-10T09:20:34Z","snapshot_observed_at":"2026-08-07T05:04:13.563975Z","submitted_at":"2025-06-10T09:20:34Z","title":"Towards Class-wise Fair Adversarial Training via Anti-Bias Soft Label Distillation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:12:28.373700Z"},"links":{"cited_paper":"/paper/2104.09425","citing_paper":"/paper/2506.08611"},"observation_digest":"sha256:4d6f76a93f2c12a0c3770af9994300735bc1af08eb1d5a8c529984d2aacebc68","observation_id":"cde2d331-ad70-4447-aaf3-d8429d5446ef","resolution":{"observed_at":"2026-08-07T05:12:28.373700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09425","last_updated":"2022-03-03T15:38:12Z","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09425","snapshot_observed_at":"2026-08-04T18:28:36.182405Z","title":"Improving adversarial robustness using proxy distributions,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09960","last_updated":"2026-06-25T13:10:45Z","snapshot_observed_at":"2026-08-07T05:03:51.320604Z","submitted_at":"2025-09-12T04:34:46Z","title":"Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T18:28:36.182405Z"},"links":{"cited_paper":"/paper/2104.09425","citing_paper":"/paper/2509.09960"},"observation_digest":"sha256:7f1138ec466979a8af5e752283aa88ac4880bf6f36e1706860431a994468cdfb","observation_id":"a1571c3f-9840-48cd-9fee-3f484376880a","resolution":{"observed_at":"2026-08-04T18:28:36.182405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09425","last_updated":"2022-03-03T15:38:12Z","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","version":3},"cited_work":{"arxiv_id":"2104.09425","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.09425","snapshot_observed_at":"2026-07-03T21:18:59.597420Z","title":"Robust learning meets generative models: Can proxy distributions improve adversarial robustness?","venue":null,"work_id":"fb130710-64f8-400a-9937-d0f7bea6e01c","year":2021},"citing_paper":{"arxiv_id":"2512.10275","last_updated":"2026-05-04T08:39:44Z","snapshot_observed_at":"2026-08-08T08:57:01.918853Z","submitted_at":"2025-12-11T04:31:04Z","title":"Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-16T23:51:34.017413Z"},"links":{"cited_paper":"/paper/2104.09425","citing_paper":"/paper/2512.10275"},"observation_digest":"sha256:f2108c70049acc44d85377f7319fec339b458df2925efea07f8eb5afc653ef75","observation_id":"3ae307d8-e640-43d7-a5ee-552632d005e8","resolution":{"observed_at":"2026-05-16T23:53:43.063273Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09425","last_updated":"2022-03-03T15:38:12Z","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","version":3},"cited_work":{"arxiv_id":"2104.09425","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.09425","snapshot_observed_at":"2026-07-03T21:18:59.597420Z","title":"Robust learning meets generative models: Can proxy distributions improve adversarial robustness?","venue":null,"work_id":"fb130710-64f8-400a-9937-d0f7bea6e01c","year":2021},"citing_paper":{"arxiv_id":"2606.18528","last_updated":"2026-06-16T22:48:44Z","snapshot_observed_at":"2026-08-08T10:10:35.690341Z","submitted_at":"2026-06-16T22:48:44Z","title":"A Prototypical Signature Approach for Writer-Independent Offline Signature Verification","version":1},"reference_index":296,"source":"arxiv_source","source_observed_at":"2026-06-27T00:39:00.630243Z"},"links":{"cited_paper":"/paper/2104.09425","citing_paper":"/paper/2606.18528"},"observation_digest":"sha256:45b0408d4df61a3ca344fd7cd2c1d3cea3dcd61695ada168e50c52452bd6097f","observation_id":"2c097312-f756-4f75-9f68-495785ee139e","resolution":{"observed_at":"2026-07-03T21:18:59.599098Z","resolver_source":"arxiv_id","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":"2104.09425","last_updated":"2022-03-03T15:38:12Z","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09425","snapshot_observed_at":"2026-08-01T11:41:31.621683Z","title":"Sehwag, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.19855","last_updated":"2026-07-22T07:43:38Z","snapshot_observed_at":"2026-08-09T10:50:42.704918Z","submitted_at":"2026-07-22T07:43:38Z","title":"Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T11:41:31.621683Z"},"links":{"cited_paper":"/paper/2104.09425","citing_paper":"/paper/2607.19855"},"observation_digest":"sha256:459737e39c69a697ffde5d2752e01d5e0c67b9741042661858a0fefb92a715da","observation_id":"b3e4c437-9187-400f-abc8-4f71cec9ebf6","resolution":{"observed_at":"2026-08-01T11:41:31.621683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2104.09425/citation-record","integrity":"/paper/2104.09425/integrity","json":"/paper/2104.09425/citation-record.json","paper":"/paper/2104.09425"},"outbound":[],"paper":{"arxiv_id":"2104.09425","last_updated":"2022-03-03T15:38:12Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T14:04:20.377069Z","submitted_at":"2021-04-19T16:17:12Z","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2104.09425."}