{"as_of":"2026-08-20T21:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:be5fc081c6ebe1482e7009826f858b876d1b0c2e3c3d7f2d84752a39e96fc0b0","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:06:49.574362Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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":"2026-06-29T14:05:30.109141Z","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":"2026-06-29T14:13:30.293874Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"cited_work":{"arxiv_id":"2506.17874","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.17874","snapshot_observed_at":"2026-06-29T14:13:30.293874Z","title":null,"venue":null,"work_id":"85fbdc9d-281d-43fd-ad9a-5b2ab0d1d41f","year":2025},"citing_paper":{"arxiv_id":"2605.28165","last_updated":"2026-05-27T08:47:50Z","snapshot_observed_at":"2026-08-08T06:00:31.662496Z","submitted_at":"2026-05-27T08:47:50Z","title":"Unification and Optimization of Robust Supervised Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T14:05:30.109141Z"},"links":{"cited_paper":"/paper/2506.17874","citing_paper":"/paper/2605.28165"},"observation_digest":"sha256:d6ac4e09ccc63789ccb76b6b02f3b5f834db3c59decb3983ba61210e099d17a3","observation_id":"942b9f5c-9521-4b3f-90e2-69cd97e4ec58","resolution":{"observed_at":"2026-06-29T14:13:30.295146Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.17874/citation-record","integrity":"/paper/2506.17874/integrity","json":"/paper/2506.17874/citation-record.json","paper":"/paper/2506.17874"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:06:49.393136Z","title":"cambridge university press, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.393136Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:bc23a45281356370e48114973797d403816d764a71c4377ce2ad2aebcf05dea9","observation_id":"3b2f9429-8d6a-4be6-b4fc-6f7c1e7ff44b","resolution":{"observed_at":"2026-08-15T19:06:49.393136Z","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":"2026-08-15T19:06:50.278977Z","title":"Wasserstein distributional robustness of neural networks, 2023","venue":null,"work_id":"cf4cbbd2-a611-4121-955a-cde0fb986829","year":2023},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.398398Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:f8fa3062f65dccf7b6f0597083871dda58fe2915e38eb2d2cf66e2b64e859a5e","observation_id":"05deb867-cd5e-4d42-a7c9-5fee8447f21c","resolution":{"observed_at":"2026-08-15T19:06:50.283753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.12022","last_updated":"2021-11-12T13:58:27Z","snapshot_observed_at":"2026-08-19T02:04:42.628440Z","submitted_at":"2020-06-22T06:26:09Z","title":"Sensitivity analysis of Wasserstein distributionally robust optimization problems","version":2},"cited_work":{"arxiv_id":"2006.12022","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.12022","snapshot_observed_at":"2026-08-15T19:06:49.902244Z","title":"Sensitivity analysis of Wasserstein distributionally robust optimization problems","venue":"math.OC","work_id":"029d4419-599b-47f0-af49-1cff44dd4d02","year":2020},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.403578Z"},"links":{"cited_paper":"/paper/2006.12022","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:97ba5e33561525a89bd2459871514561b7e4254ce35704c9df358d48990588f8","observation_id":"d9a40109-6958-4ce7-9352-a91191d832ac","resolution":{"observed_at":"2026-08-15T19:06:49.907589Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.264119Z","title":"Almost linear vc dimension bounds for piecewise polynomial networks.Advances in neural information processing systems, 11, 1998","venue":null,"work_id":"92160106-489f-4742-8740-084343969cf3","year":1998},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.408984Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:bf125f059d8e4a15ee64121f58a1d703016223e605d42adc50f0ae5de145fd83","observation_id":"ceeb9c1b-749c-45c7-aef1-65c8d83e5907","resolution":{"observed_at":"2026-08-15T19:06:50.268962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.249006Z","title":"Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations","venue":null,"work_id":"c2bc90e6-8c8e-448d-aea5-0bb9934fb716","year":2023},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.414046Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:a29054df7d90babac4bd63dfec68177c2b3e80a15cba05fe309c3d570420af7a","observation_id":"4fd3c7ad-d453-41b1-81fd-949c445b33a5","resolution":{"observed_at":"2026-08-15T19:06:50.254188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.231717Z","title":"Deep neural networks for nonparametric interaction models with diverging dimension.The Annals of Statistics, 52(6):2738–2766, 2024","venue":null,"work_id":"0b5ee044-f5fe-4e47-bfc6-f30c2cc92844","year":2024},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.418710Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:7788c6efd72ecabe75d29becbf2f7720984285ae99317fedd0136bb20a90c835","observation_id":"37501ffa-0303-4ee8-9319-87f8fd6ec49b","resolution":{"observed_at":"2026-08-15T19:06:50.237395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.212543Z","title":"Multivariate distributionally robust convex regression under absolute error loss.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"cf587e74-f476-4b5f-847b-91d265929cb4","year":2019},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.424742Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:7cadff680fe4ca94bf09ed82d73af8e43b9b369246ba50e59c3938444bc79e66","observation_id":"f9909e6d-7e60-4e46-8fe9-2752d0232788","resolution":{"observed_at":"2026-08-15T19:06:50.217629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.196864Z","title":"Robust wasserstein profile inference and applications to machine learning.Journal of Applied Probability, 56(3):830–857, 2019","venue":null,"work_id":"38caf11b-ebf5-496e-8bb3-f1c09daeb02d","year":2019},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.429547Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:63664cf7f1bfd536ee8d9d96b191022c6ad25e6fe1c3ada111922982fc7d76b2","observation_id":"b48b35d9-b19d-4116-b972-baba337ce070","resolution":{"observed_at":"2026-08-15T19:06:50.201880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.181054Z","title":"Confidence regions in wasserstein distributionally robust estimation.Biometrika, 109(2):295–315, 2022","venue":null,"work_id":"65738ced-b25c-4e86-a5a4-af20d1be6fcb","year":2022},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.434806Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:a6ed65e39befc96aa58158f7038ed4d5cac253dae90f17137870c0646f7740e4","observation_id":"d7bb405b-4f4b-4549-8101-c166708edff4","resolution":{"observed_at":"2026-08-15T19:06:50.186130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.166292Z","title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","venue":null,"work_id":"8325443e-e68b-4f01-900c-95bdf0c21c71","year":2016},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.439464Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:61252503f9880b015ed491b81ea82ec416b563a485761cd1424e531bc0d1f5e7","observation_id":"a25ea303-b7ad-4c43-abfb-6521eaa8b14b","resolution":{"observed_at":"2026-08-15T19:06:50.170535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.152015Z","title":"Distributionally robust multiclass classification and applications in deep cnn image classifiers.stat, 1050:27, 2021","venue":null,"work_id":"06f9be01-be4d-446d-8964-fda5c3ddf024","year":2021},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.444533Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:143807680f8d48b52a5ec64c623e19e1214e078814b145632c90afe8d839be59","observation_id":"18b7ffed-8fbb-4706-b417-563a61f091a0","resolution":{"observed_at":"2026-08-15T19:06:50.156724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:49.449751Z","title":"A robust learning approach for regression models based on distributionally robust optimization.Journal of Machine Learning Research, 19(13):1–48, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.449751Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:1ada4ad7ae67ffa069350bafbfd866abd7e6ba4f252124e5148be85796451066","observation_id":"90b3e7bf-9864-4554-9fe3-cca8d64cfbae","resolution":{"observed_at":"2026-08-15T19:06:49.449751Z","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":"2026-08-15T19:06:49.454377Z","title":"Distributionally robust optimization under moment uncertainty with application to data-driven problems.Operations research, 58(3):595–612, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.454377Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:054c14726dfa91cbe6d3e9e6030376f63409efda2084d3389a8b02db0bdd47c4","observation_id":"06250727-ff7e-4a1b-8c39-6829565fea8f","resolution":{"observed_at":"2026-08-15T19:06:49.454377Z","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":"2026-08-15T19:06:49.458749Z","title":"Bert: Pre-training of deep bidi- rectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.458749Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:3fcab78184bf593b6922836bb4b574a180f6d62dcea1b53abd14b7250887d1ea","observation_id":"0d2a6f40-414b-44e3-8dab-3f65cacf4821","resolution":{"observed_at":"2026-08-15T19:06:49.458749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.01263","last_updated":"2022-05-23T01:33:54Z","snapshot_observed_at":"2026-08-20T04:00:12.985332Z","submitted_at":"2022-02-02T19:53:35Z","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01263","snapshot_observed_at":"2026-08-15T19:06:49.463411Z","title":"Noisymix: Boosting model robustness to common corruptions.arXiv preprint arXiv:2202.01263, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.463411Z"},"links":{"cited_paper":"/paper/2202.01263","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:05044bbd7899d21115afd7cd654d31d6df756b41af355753d9ed27b4fb6ef50d","observation_id":"93d71caa-6507-4228-9fc6-5e10aa8f99f5","resolution":{"observed_at":"2026-08-15T19:06:49.463411Z","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":"2026-08-15T19:06:49.468246Z","title":"Wasserstein distributionally robust optimization and variation regularization.Operations Research, 72(3):1177–1191, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.468246Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:ac99e31d6da802490c63ce76f611c832d343f2ec097069ba123be815a05655f3","observation_id":"c68aeb3d-a800-4843-9373-6200f56406b2","resolution":{"observed_at":"2026-08-15T19:06:49.468246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.06732","last_updated":"2018-07-20T01:57:37Z","snapshot_observed_at":"2026-08-14T18:50:43.034747Z","submitted_at":"2018-07-18T01:17:27Z","title":"Motivating the Rules of the Game for Adversarial Example Research","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.06732","snapshot_observed_at":"2026-08-15T19:06:49.472455Z","title":"Motivating the rules of the game for adversarial example research.arXiv preprint arXiv:1807.06732, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.472455Z"},"links":{"cited_paper":"/paper/1807.06732","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:8739346981f9851afcb34552aae6ba86426f93c538b14e8a1d6fcdb08de91c9d","observation_id":"7efca5d8-3f97-4147-9741-67773d8657c1","resolution":{"observed_at":"2026-08-15T19:06:49.472455Z","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":"2026-08-15T19:06:49.477147Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.477147Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:714ea683c5850788a9d1b9356794562e2d4c0f084839e2871346834ac88fcd65","observation_id":"5d322ae7-0d1a-47b8-b277-27151c1d4740","resolution":{"observed_at":"2026-08-15T19:06:49.477147Z","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":"2026-08-15T19:06:50.087615Z","title":"Identity mappings in deep residual networks","venue":null,"work_id":"16d0b6bb-3854-4357-8301-b8733fab4cf6","year":2016},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.481154Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:d389fa0ef49242a16047cbab92055a84f5a4ed75421129b4d2cf162ae06fa2c7","observation_id":"bd34912b-5465-4197-a3d5-68d73d703161","resolution":{"observed_at":"2026-08-15T19:06:50.092532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.12261","last_updated":"2019-03-28T20:56:37Z","snapshot_observed_at":"2026-08-15T10:34:34.836991Z","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.12261","snapshot_observed_at":"2026-08-15T19:06:49.485268Z","title":"Benchmarking neural network robustness to common corruptions and perturbations.arXiv preprint arXiv:1903.12261, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.485268Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:309ab3f7d330b1f5f4151f06a16e1320ff2e7e1250d0b69a5bf9b3716309c281","observation_id":"30102c67-9e5a-459f-b3d2-608e98091ff0","resolution":{"observed_at":"2026-08-15T19:06:49.485268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02781","last_updated":"2020-02-17T06:16:13Z","snapshot_observed_at":"2026-08-19T03:25:32.888684Z","submitted_at":"2019-12-05T18:18:10Z","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02781","snapshot_observed_at":"2026-08-15T19:06:49.489738Z","title":"Augmix: A simple data processing method to improve robustness and uncertainty.arXiv preprint arXiv:1912.02781, 2019","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.489738Z"},"links":{"cited_paper":"/paper/1912.02781","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:aaa074f1265848e88af610d2e6c510228f448731b09237f7f24b855e1cd7dea4","observation_id":"d096ea3d-b858-488d-b612-d5cf5bffc5cb","resolution":{"observed_at":"2026-08-15T19:06:49.489738Z","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":"2026-08-15T19:06:50.071604Z","title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups.IEEE Signal processing magazine, 29(6):82–97, 2012","venue":null,"work_id":"e18ce57b-110c-4013-8b4b-e8a8e0cd3def","year":2012},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.494010Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:5e7455b814049e07a3d474ecfdb803277580ee16766dcf7c320a2bde9d6c9d39","observation_id":"4700f218-cc19-4a34-8bf8-d22cacfa6e32","resolution":{"observed_at":"2026-08-15T19:06:50.076797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:50.055761Z","title":"Adversarial classification via distributional robustness with wasserstein ambiguity.Mathematical Programming, 198(2):1411–1447, 2023","venue":null,"work_id":"020c0e15-3e9d-4142-b54c-68dd6e08b83c","year":2023},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.497739Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:f71ff654a72973b11390d7751d6825eb85d2d29c34b970a6bb89dcab724102ce","observation_id":"10b94cf1-b946-4ccf-80ab-a883f913accb","resolution":{"observed_at":"2026-08-15T19:06:50.060993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:49.501442Z","title":"On the rate of convergence of fully connected deep neural network regression estimates.The Annals of Statistics, 49(4):2231–2249, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.501442Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:d8e2122ac71da1c4a4377327eb79fc1e33f709c9cc48c3440cc7c072d12f8603","observation_id":"d1581ec5-4878-4c45-8b4a-2f6b61991348","resolution":{"observed_at":"2026-08-15T19:06:49.501442Z","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":"2026-08-15T19:06:49.505487Z","title":"Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.505487Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:e7b7999b6e359a36e543a5a7ee42c4d2e8533bf283f96070cbf7699ff69761da","observation_id":"6354adf3-3451-4412-9b50-6560a4191565","resolution":{"observed_at":"2026-08-15T19:06:49.505487Z","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":"2026-08-15T19:06:49.509970Z","title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.509970Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:744c371e53a0a1ac43bbbba1e94b77eaa2eb2f31e4802e09034884fb89660693","observation_id":"63621c65-914b-43c9-82b6-f2b1cc4e7b94","resolution":{"observed_at":"2026-08-15T19:06:49.509970Z","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":"2026-08-15T19:06:50.009951Z","title":"Nonasymptotic bounds for adversarial excess risk under misspecified models.SIAM Journal on Mathematics of Data Science, 6(4):847–868, 2024","venue":null,"work_id":"2ade128f-6b59-4853-8120-248d51161f37","year":2024},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.514480Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:b14be2e7119765fe395506a0c3bd16465166abbf05bf6f6939adb0cc0f2ff8d6","observation_id":"d1507092-53b8-4843-b7a9-e4a4ea78092c","resolution":{"observed_at":"2026-08-15T19:06:50.015124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:49.518713Z","title":"Towards deep learning models resistant to adversarial attacks.stat, 1050(9), 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.518713Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:d7dd660b12c5016beed72f45d992b85d8a64a6e867a600fbe71760307a393ac1","observation_id":"a9043595-5b26-431c-9992-c9cc454b9f10","resolution":{"observed_at":"2026-08-15T19:06:49.518713Z","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":"2026-08-15T19:06:49.983260Z","title":"Data-driven distributionally robust optimization using the wasserstein metric: Performance guarantees and tractable reformulations.Mathematical Programming, 171(1):115–166, 2018","venue":null,"work_id":"9c23bfaf-349c-4b94-b9e6-0212bad8567d","year":2018},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.523034Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:f23d5e54d8f3b4d041487ce5f889d77f6d47c91f260af1215b4ee0b6dabaf29b","observation_id":"ab83bdc3-640c-44df-904a-b3878ff433fa","resolution":{"observed_at":"2026-08-15T19:06:49.988184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:49.968057Z","title":"A simple way to make neural networks robust against diverse image corruptions","venue":null,"work_id":"5b1d7398-3083-4c4e-8e75-137ce68e9593","year":2020},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.527450Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:1741217f6542d49c561cf2ec1ce731070e127227303bd9b65f7673d8411a3328","observation_id":"08194289-39fb-472f-a888-7393dd1f70b3","resolution":{"observed_at":"2026-08-15T19:06:49.972467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:06:49.531855Z","title":"Nonparametric regression using deep neural networks with relu activation function","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.531855Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:33768c996e4442b5c3697dd96cd0fc6a41c0dde5927307309f4ea993982e3611","observation_id":"55d7d5a6-b0e2-4855-899a-332fc0f1a80b","resolution":{"observed_at":"2026-08-15T19:06:49.531855Z","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":"2026-08-15T19:06:49.940565Z","title":"Distributionally robust logistic regression.Advances in neural information processing systems, 28, 2015","venue":null,"work_id":"9eccb021-1859-49ff-8174-9561bb9e541d","year":2015},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.536141Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:f0311ff22b9a887ff31773dbd9adcc00e07a83208839f40e60c64b50420a75bf","observation_id":"d6fd6cb0-ded7-4547-9c74-bc9ee129fa63","resolution":{"observed_at":"2026-08-15T19:06:49.946167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10571","last_updated":"2020-05-01T07:29:34Z","snapshot_observed_at":"2026-08-20T04:15:35.155856Z","submitted_at":"2017-10-29T07:27:57Z","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10571","snapshot_observed_at":"2026-08-15T19:06:49.540461Z","title":"Certifiable distributional robustness with principled adversarial training","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.540461Z"},"links":{"cited_paper":"/paper/1710.10571","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:32ef20a283401e8b50da1e6bc4afb71bed52cf2394e9447d475820aaf12de5a1","observation_id":"a6d40ee1-e43f-4869-882d-03fd8065c992","resolution":{"observed_at":"2026-08-15T19:06:49.540461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-08-15T16:41:15.505782Z","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":"2026-08-15T19:06:49.545443Z","title":"Intriguing properties of neural networks.arXiv preprint arXiv:1312.6199, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.545443Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:3d805c059f999e5c23871d79ade42c03c3e37b2de4715aa50f10083956b1299c","observation_id":"c442dc18-f0ef-482f-95d0-0c022f15d024","resolution":{"observed_at":"2026-08-15T19:06:49.545443Z","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":"2026-08-15T19:06:49.550257Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.550257Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:5dcfce5280b2e7558bb5c002acb5836c7eb029c46c7cdc8c5029563be5121419","observation_id":"3952d2f8-6b95-4200-a825-a711af83dd45","resolution":{"observed_at":"2026-08-15T19:06:49.550257Z","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":"2026-08-15T19:06:49.554848Z","title":"Cambridge university press, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.554848Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:561106e8cf58a201706b161310b85486439d546ddf535d238d1cc929a436d207","observation_id":"6df3d87a-032e-4610-aee4-375718601fd3","resolution":{"observed_at":"2026-08-15T19:06:49.554848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-15T19:06:49.559435Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms.arXiv preprint arXiv:1708.07747, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.559435Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:c3e5938e7ff0b54e9ed3ae2b3ce643b5a108e6bd59491419c12a5683632aa24f","observation_id":"2bfb432a-e942-4505-9aa7-57c87be0c1a5","resolution":{"observed_at":"2026-08-15T19:06:49.559435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-15T19:06:49.564438Z","title":"mixup: Beyond empirical risk minimization.arXiv preprint arXiv:1710.09412, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.564438Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:84eed4570c069df1e2a6fd8c6e73b5f5b44e9c541a11c42b8f59d3c83f6c9750","observation_id":"8464f8c5-7204-4988-983e-644627b8d9dc","resolution":{"observed_at":"2026-08-15T19:06:49.564438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.04819","last_updated":"2021-03-17T19:43:43Z","snapshot_observed_at":"2026-08-17T21:16:40.136584Z","submitted_at":"2020-10-09T21:38:14Z","title":"How Does Mixup Help With Robustness and Generalization?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.04819","snapshot_observed_at":"2026-08-15T19:06:49.569263Z","title":"How does mixup help with robustness and generalization?arXiv preprint arXiv:2010.04819, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.569263Z"},"links":{"cited_paper":"/paper/2010.04819","citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:63f62a005756cfd7a76a302878a30df5037aa0390f6d0c22d4c08443c138c631","observation_id":"22547074-f937-481d-a673-a9e0581a1cad","resolution":{"observed_at":"2026-08-15T19:06:49.569263Z","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":"1667.5486","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:06:49.733882Z","title":"Improving the robustness of deep neural networks via stability training","venue":null,"work_id":"a8593922-3ec0-443f-8539-fb5d54632b94","year":1959},"citing_paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T19:06:49.574362Z"},"links":{"citing_paper":"/paper/2506.17874"},"observation_digest":"sha256:24ae142d65671d0e1e19918ab3727b881d1d1ef526ec64a43493633ee5dd5eeb","observation_id":"3fb1507b-2fc9-4e5e-b5d1-88dbf6f3b9dd","resolution":{"observed_at":"2026-08-15T19:06:49.743292Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.17874","last_updated":"2025-06-24T21:04:53Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-19T01:38:20.259461Z","submitted_at":"2025-06-22T02:18:03Z","title":"DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":22,"verified_exact":0,"verified_fuzzy":16},"total_outbound_references":40},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2506.17874."}