{"as_of":"2026-08-13T13:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9d12b779622e867a300f655f05baa9fcc8794cb708e4b29fd783b26854af92ab","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:43:40.311726Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.17959/citation-record","integrity":"/paper/2411.17959/integrity","json":"/paper/2411.17959/citation-record.json","paper":"/paper/2411.17959"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T11:43:42.647402Z","title":"Are labels required for improving adversarial robustness? Ad- vances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"620a649c-8592-42f2-822c-2f7bd7b567d7","year":2019},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.804128Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:56e8353e450367d449463092aa11344dd1aa05c05f9543216b18ca0b1b25c67d","observation_id":"ca08fc3b-0812-403a-bda0-92b9087e60b5","resolution":{"observed_at":"2026-08-12T11:43:42.656953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:39.809237Z","title":"Square attack: a query-efficient black-box adversarial attack via random search","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.809237Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:8f1afe3783d0addfc9e395871c2a0eb106167054c7e917045fa267a91533c156","observation_id":"42af87cb-ba14-48d8-ab10-5aaa6513d3ca","resolution":{"observed_at":"2026-08-12T11:43:39.809237Z","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":"2026-08-12T11:43:42.579309Z","title":"Curriculum adver- sarial training","venue":null,"work_id":"0c202fb7-16fa-495e-bf2c-a3314d6bfd5f","year":2018},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.821504Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:6209dc4a74a0002b6c76624018ddef8ac54329f4e3b2092f34aec15f1825ec15","observation_id":"172ac1df-100d-45b2-973d-39f3bf31ee68","resolution":{"observed_at":"2026-08-12T11:43:42.613756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:42.442030Z","title":"Unlabeled data improves adver- sarial robustness","venue":null,"work_id":"1ce95065-5002-44fb-bc7b-ccc7a08e6ac9","year":2019},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.840915Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:790111def46faff318cc4ae69d3fe335aab88055776cd2a6da40e0b42fc35f8b","observation_id":"27192130-3f53-4901-ada9-0f90ea058a77","resolution":{"observed_at":"2026-08-12T11:43:42.512311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06789","last_updated":"2020-02-17T06:13:05Z","snapshot_observed_at":"2026-08-13T10:28:38.393754Z","submitted_at":"2020-02-17T06:13:05Z","title":"CAT: Customized Adversarial Training for Improved Robustness","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06789","snapshot_observed_at":"2026-08-12T11:43:39.877694Z","title":"Cat: Customized adversarial training for im- proved robustness","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.877694Z"},"links":{"cited_paper":"/paper/2002.06789","citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:18f36aaf680c6a363143505c5297212252e2e81b26472d16932f612c2a8e4fda","observation_id":"8abf1769-1b21-4a29-a381-b93a4e7444ff","resolution":{"observed_at":"2026-08-12T11:43:39.877694Z","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":"2026-08-12T11:43:42.347774Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter- free attacks","venue":null,"work_id":"89adf876-4b43-4a24-8395-47cf91022630","year":2020},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.954256Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:e9dba83caf4936cf5e3e1e36bb713447f2cff84d6a062f3dbf96c8be9cad33d6","observation_id":"41186f6e-87a7-4be1-b2ce-b0589653d6e9","resolution":{"observed_at":"2026-08-12T11:43:42.411671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:42.164912Z","title":"Minimally distorted adversarial examples with a fast adaptive boundary attack","venue":null,"work_id":"4f372fe8-6f9f-4b15-bc2c-3983dc42a019","year":null},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:39.978040Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:7b543284e7c44d03848fa57567c0c1db5bb5fbb6695e53fdc081d25f7a36e5d5","observation_id":"c0e3f4cc-5091-4b58-b7b9-576ae5feb342","resolution":{"observed_at":"2026-08-12T11:43:42.247194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:41.827943Z","title":"Mma training: Direct input space margin maximization through adversarial training","venue":null,"work_id":"6086da7e-0193-4074-88bd-5458fe68275d","year":2020},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.012933Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:a833951f9e20acd584277dd605ee5e5f82c8a477ed8f667fc055e85b1ae763d7","observation_id":"7e9f7877-92ef-4db9-986a-98d15fcf5fd6","resolution":{"observed_at":"2026-08-12T11:43:41.995550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.037399Z","title":"Robust physical-world attacks on deep learning visual classification","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.037399Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:d2b4d111373f8d8eb52bcbca8dfc9f0dd94982eff5576816a83340e202c15ce0","observation_id":"2f089e38-2aa1-4f85-8a34-4d2ee531bd05","resolution":{"observed_at":"2026-08-12T11:43:40.037399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.05296","last_updated":"2019-02-04T06:03:22Z","snapshot_observed_at":"2026-08-10T08:46:28.017860Z","submitted_at":"2018-04-15T02:33:08Z","title":"Adversarial Attacks Against Medical Deep Learning Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.05296","snapshot_observed_at":"2026-08-12T11:43:40.052784Z","title":"Adversarial attacks against medical deep learning systems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.052784Z"},"links":{"cited_paper":"/paper/1804.05296","citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:a1739c1e538a684fc7ae45167198cd52d8f45efe7a5504ed5d49e59952c3a575","observation_id":"9509c0c2-7dde-4121-a4fc-e9276506aaa0","resolution":{"observed_at":"2026-08-12T11:43:40.052784Z","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":"2026-08-12T11:43:41.585601Z","title":"Goodfellow, Jonathon Shlens, and Christian Szegedy","venue":null,"work_id":"f54c4278-193a-4e1c-a5ed-1deb5f630edf","year":2015},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.079633Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:4328fb71eedb2409017d5afa01c0bac482b0c0f62d8fcc461cfe4bd805cb7e33","observation_id":"6a67aa9d-0493-41df-aca0-e57dcfa87705","resolution":{"observed_at":"2026-08-12T11:43:41.660106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:41.390268Z","title":"Adversarial examples are not bugs, they are features","venue":null,"work_id":"3d188256-cf49-42bb-b8d6-5ecc1d6c316d","year":2019},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.095563Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:577967c332a996a68cb311acb68a6556a180d589b309608016a4143698660223","observation_id":"2ea101be-9ffa-4b09-b289-7fb027f46fe9","resolution":{"observed_at":"2026-08-12T11:43:41.493329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.099767Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.099767Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:bac3e71c3e35c54e7b690eb6f3345075bcf73414ccef48dd6dfadbf32445f82d","observation_id":"9880b263-670e-4295-bb53-3e2b6654c0d6","resolution":{"observed_at":"2026-08-12T11:43:40.099767Z","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":"2026-08-12T11:43:41.204477Z","title":"Adver- sarial examples in the physical world, 2017","venue":null,"work_id":"0cfb5138-0343-4e5f-8069-de6ae4a27de1","year":2017},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.104604Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:8e4ed3e0a2dec52e4f6b3909e3e083d952f11f7f8cd8482b74930058f560825c","observation_id":"ecd1ae07-a700-43a4-82da-0be1d0b44b9d","resolution":{"observed_at":"2026-08-12T11:43:41.287788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:41.039928Z","title":"Probabilistic mar- gins for instance reweighting in adversarial training.Advances in Neural Information Processing Systems, 34:23258–23269,","venue":null,"work_id":"28fd8617-6fb8-428e-b52b-2771e0e07d9b","year":null},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.108646Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:9da769b9ee0c2c4cd9950c8afcdc05913fbea86b3115260082263d8878820305","observation_id":"8a7ff5a3-a10e-4e8c-b63e-7fc60f5c2cca","resolution":{"observed_at":"2026-08-12T11:43:41.099398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.112630Z","title":"Towards deep learn- ing models resistant to adversarial attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.112630Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:6c6f12c6c9d8db720d030d21cdec53ea48db1884e8e96104eb17b665c83dfc75","observation_id":"a48881d5-7c54-447e-ae98-0b5e46ab6497","resolution":{"observed_at":"2026-08-12T11:43:40.112630Z","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":"2026-08-12T11:43:41.019352Z","title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","venue":null,"work_id":"192a40d0-5a9c-4ab3-8f2f-4dbc6e493e81","year":1979},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.116484Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:73899c0f1e032f5d4fb3b7eaf81b03fb228b819c659e66b3ce06fb5c03b8de36","observation_id":"f803b4de-cdca-4f69-b734-03415ad7dc34","resolution":{"observed_at":"2026-08-12T11:43:41.023657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:41.006390Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"20e25631-6ee9-4d8b-aa07-85b52d2f9b91","year":2011},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.121918Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:05f411a9eae28875c35fc5f4332b6e51bff405d86921c150767d155b06b82dea","observation_id":"cf8b1906-4f50-4c73-be3f-03ebfebc42ff","resolution":{"observed_at":"2026-08-12T11:43:41.011338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.985823Z","title":"Reducing excessive margin to achieve a better accuracy vs","venue":null,"work_id":"f8680e50-4ab2-463e-ad4f-8f114499e55f","year":2021},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.126149Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:3819ce29748bc68fc362e22d92b4897d99af3ba5330cc0ab700449fd5a614d41","observation_id":"6c3b9d52-cec9-4dc5-a9ae-aca746b684d2","resolution":{"observed_at":"2026-08-12T11:43:40.997130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.879488Z","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","venue":null,"work_id":"c293f32c-6240-42e2-bfab-43dca840062c","year":2020},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.129864Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:b56211df02f31e7d526d88d59af608a046b8b30e139d4564bec06fe3cfb437a2","observation_id":"560600da-d21a-482d-af9a-eca8bdfaccc4","resolution":{"observed_at":"2026-08-12T11:43:40.923643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.808411Z","title":"Fooling automated surveillance cameras: adversarial patches to attack person detection","venue":null,"work_id":"341d8c95-afe9-46d2-9f91-c189c617f959","year":2019},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.133670Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:aa5b1388e703ffb3d130709a4c50a6d6a15f2c980662a5bb8234a9dd400d312a","observation_id":"d1d11270-b7ec-419d-bd30-122170283e46","resolution":{"observed_at":"2026-08-12T11:43:40.845790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.785592Z","title":"Robustness may be at odds with accuracy","venue":null,"work_id":"a9a8a993-8023-403e-87c5-39e995a54d46","year":2019},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.137410Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:97f42a1382e7be62604d092437253989a9ec7c078ad68cf5fc3012f9703fd73c","observation_id":"d23a322f-2bc7-4712-945e-cd48a0de06a3","resolution":{"observed_at":"2026-08-12T11:43:40.791470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.766051Z","title":"Improving adversarial robustness requires revisiting misclassified examples","venue":null,"work_id":"88abb461-2b46-467c-939b-97da31017288","year":2019},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.141274Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:c7afa4c12d8c4e9cd82ae1a7e93b15052c3feaf411ce4ca8f271eae8ca20df72","observation_id":"f736001d-86b0-4b43-a6c9-da774cebbd41","resolution":{"observed_at":"2026-08-12T11:43:40.773359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.743555Z","title":"Adversarial driving: Attacking end-to- end autonomous driving","venue":null,"work_id":"ad3c75e6-073d-44f1-9038-0ab6bb6d8008","year":2023},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.144586Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:48d4b90d97f0507c345c5716bbca3ba130bfdb31baad883678554d9777cb9b23","observation_id":"916d50b7-cfb3-4b34-8b93-8b0f23f67689","resolution":{"observed_at":"2026-08-12T11:43:40.748813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.693683Z","title":"Improving adversarial robustness by putting more regularizations on less robust samples","venue":null,"work_id":"c37d7e45-c641-469d-982c-3da6629e0761","year":2023},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.147902Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:70035a2daac882d5cea27d6593f85ee4f9b846000b26bcdce9527c2b29e16f43","observation_id":"6aef80ff-a710-4cf7-a28a-307d12946fe1","resolution":{"observed_at":"2026-08-12T11:43:40.721018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.645526Z","title":"Enhanc- ing adversarial robustness in low-label regime via adaptively weighted regularization and knowledge distillation","venue":null,"work_id":"cbb465cf-e225-494f-9083-6266bd16d730","year":2023},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.151740Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:f8b400a3e359216c397df6fc2af8c171d553d4048d5eb35cfe995c222fcbfb43","observation_id":"e5a7481b-4b27-4487-8899-6b79acdb364d","resolution":{"observed_at":"2026-08-12T11:43:40.667150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.589652Z","title":"One size does not fit all: Data- adaptive adversarial training","venue":null,"work_id":"947f868a-252a-4247-a348-7e4e96289135","year":2022},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.156127Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:40a91c4546d8f9deb1b7f17b24f37ef9323568e720a88cda63cfebd24aaf88ff","observation_id":"88a803e0-045e-4b98-b0e5-f842cbe93ea2","resolution":{"observed_at":"2026-08-12T11:43:40.623576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.478548Z","title":"Wide residual networks","venue":null,"work_id":"f3be9283-75a5-45bf-83dc-c09528f91c76","year":2016},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.160025Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:2bb5132ba6835f6477bf8842681ad2f10716b631ae05ee659d6b6dd2b3f9ccd6","observation_id":"2de91f8d-6ba5-4aff-a0d1-7ca24d8c14bf","resolution":{"observed_at":"2026-08-12T11:43:40.555928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:43:40.180258Z","title":"Theoretically principled trade-off between robustness and accuracy","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.180258Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:7395d940c908f85451c60043b7e6093004d3465faa394a18da4d9e9244b54614","observation_id":"c0f5c482-eef2-4002-9252-492bcd9e71e2","resolution":{"observed_at":"2026-08-12T11:43:40.180258Z","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":"2026-08-12T11:43:40.458469Z","title":"Attacks which do not kill training make adversarial learning stronger","venue":null,"work_id":"2305ca3f-4550-4cb7-8ca8-0ca027a509e6","year":2020},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.231764Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:ffce0059cba46536edbcff09f03a28668d2da5ed79d48298393c5299b0045942","observation_id":"acaebdc1-aef7-44b8-85f0-630d9458d5ea","resolution":{"observed_at":"2026-08-12T11:43:40.462301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01736","last_updated":"2021-05-31T02:49:55Z","snapshot_observed_at":"2026-07-06T10:01:23.472948Z","submitted_at":"2020-10-05T01:33:11Z","title":"Geometry-aware Instance-reweighted Adversarial Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01736","snapshot_observed_at":"2026-08-12T11:43:40.291672Z","title":"Geometry-aware instance-reweighted adversarial training","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.291672Z"},"links":{"cited_paper":"/paper/2010.01736","citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:135ef8b85e5945d9534345fecc31117947b66186504d72ceee1952ccaa27a9b0","observation_id":"12de1bfb-83a2-43bf-b317-c7d0f3f96eb3","resolution":{"observed_at":"2026-08-12T11:43:40.291672Z","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":"2026-08-12T11:43:40.386380Z","title":"Curious” refers to global epsilon scheduling CURIOUS -(1.25, 70). “Const","venue":null,"work_id":"cb976ee8-c536-4e2e-ba04-6e8a547c721b","year":null},"citing_paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T11:43:40.311726Z"},"links":{"citing_paper":"/paper/2411.17959"},"observation_digest":"sha256:2bf57583df9d83ad29573fd97d9895bea9d731ec7f159d59da8ac60f068fce0e","observation_id":"d7b962ac-9dc8-4e66-bd1a-4ca1696ea11e","resolution":{"observed_at":"2026-08-12T11:43:40.434009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.17959","last_updated":"2024-11-27T00:35:13Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T11:37:24.009082Z","submitted_at":"2024-11-27T00:35:13Z","title":"Adversarial Training in Low-Label Regimes with Margin-Based Interpolation"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":24},"total_outbound_references":32},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2411.17959."}