{"as_of":"2026-08-22T10:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:21e1363a84db312ebf9c9b24b87c2157755c606b2a5cd124a474d818653f85ec","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":31,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:59:52.396711Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T13:08:08.786365Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":"2005.05909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-07-03T13:08:08.786365Z","title":"In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations","venue":null,"work_id":"14c74400-036d-491d-b0c3-76e6bf1b4fbb","year":2005},"citing_paper":{"arxiv_id":"2309.00614","last_updated":"2023-09-04T17:47:36Z","snapshot_observed_at":"2026-07-06T16:13:23.343694Z","submitted_at":"2023-09-01T17:59:44Z","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-13T23:24:39.835347Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2309.00614"},"observation_digest":"sha256:4fece9b0a620138d576772feebf401748351587b30c1beb2dc01a0f8707165ed","observation_id":"8ad5dda9-6ee8-4b66-a6b3-5ea4c1bd3df3","resolution":{"observed_at":"2026-05-13T23:24:40.176671Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":"2005.05909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-07-03T13:08:08.786365Z","title":"In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations","venue":null,"work_id":"14c74400-036d-491d-b0c3-76e6bf1b4fbb","year":2005},"citing_paper":{"arxiv_id":"2310.03684","last_updated":"2024-06-11T19:02:52Z","snapshot_observed_at":"2026-08-17T15:25:03.596568Z","submitted_at":"2023-10-05T17:01:53Z","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","version":4},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-14T17:11:00.639293Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2310.03684"},"observation_digest":"sha256:6409ecfa211b243417c0c62001d2be9c003b50832b02a20d0c891c1ad99a0de0","observation_id":"37ff3ae8-ba55-43cf-93a6-bd49b1340fee","resolution":{"observed_at":"2026-05-14T17:11:00.925500Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-12T19:37:58.422888Z","title":"arXiv:2005.05909 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.10565","last_updated":"2025-05-05T22:01:36Z","snapshot_observed_at":"2026-08-19T11:40:12.737036Z","submitted_at":"2024-11-15T20:25:32Z","title":"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-12T19:37:58.422888Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2411.10565"},"observation_digest":"sha256:863bc50e6f0835a14504a7ee8c4cc8cda1c44ea9c69ff4cc5ca806e045b56e1e","observation_id":"0e26e03a-06b2-4682-b32d-8c88a990b433","resolution":{"observed_at":"2026-08-12T19:37:58.422888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-12T04:20:52.715422Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01495","last_updated":"2024-12-02T13:48:41Z","snapshot_observed_at":"2026-08-18T21:09:00.053747Z","submitted_at":"2024-12-02T13:48:41Z","title":"Adversarial Attacks on Hyperbolic Networks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T04:20:52.715422Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2412.01495"},"observation_digest":"sha256:102a734ce810d243eff3a40d83e3283252b82298d7455b7b9b297e095f6875d5","observation_id":"d663a512-83b9-41fb-9a5b-7f0009bd9ca7","resolution":{"observed_at":"2026-08-12T04:20:52.715422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-11T23:10:26.157719Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.02795","last_updated":"2024-12-03T19:54:32Z","snapshot_observed_at":"2026-08-18T14:54:00.705149Z","submitted_at":"2024-12-03T19:54:32Z","title":"Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T23:10:26.157719Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2412.02795"},"observation_digest":"sha256:a4ff9ea3e8a78f1b4445ad41f28c9a6f02a5a73c604fae61f57a8050d7b38da7","observation_id":"8a7421a1-4cfa-4828-a159-2125bc2ae16e","resolution":{"observed_at":"2026-08-11T23:10:26.157719Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-11T18:18:55.028265Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.028265Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:101ef50bc7817292fc73914a356341574fdf4b0fa26ea4e07d1e27f12e4744ca","observation_id":"16c52e12-2b80-400c-849e-4ade236a231b","resolution":{"observed_at":"2026-08-11T18:18:55.028265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-11T15:40:53.177612Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.10805","last_updated":"2024-12-14T12:10:38Z","snapshot_observed_at":"2026-08-18T03:06:14.310159Z","submitted_at":"2024-12-14T12:10:38Z","title":"Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T15:40:53.177612Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2412.10805"},"observation_digest":"sha256:91e7f02c5c858c5edada73f07929ab01d900c5c065cb31147599b574c3238f48","observation_id":"a4b67705-c050-4d08-af0b-1b947052ebab","resolution":{"observed_at":"2026-08-11T15:40:53.177612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-11T15:41:57.293134Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.10807","last_updated":"2025-06-12T10:17:02Z","snapshot_observed_at":"2026-08-22T09:04:09.684194Z","submitted_at":"2024-12-14T12:11:26Z","title":"Towards Action Hijacking of Large Language Model-based Agent","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T15:41:57.293134Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2412.10807"},"observation_digest":"sha256:d13dcdc260028743b4b6fba75723395c6cd62a180f028ad899402feb6ac591a8","observation_id":"85cddb54-5b88-467a-8350-483f582ab7fb","resolution":{"observed_at":"2026-08-11T15:41:57.293134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-10T21:25:34.494112Z","title":"arXiv preprint arXiv:2005.05909 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.04985","last_updated":"2025-01-09T06:00:08Z","snapshot_observed_at":"2026-08-20T19:00:15.177131Z","submitted_at":"2025-01-09T06:00:08Z","title":"SpaLLM-Guard: Pairing SMS Spam Detection Using Open-source and Commercial LLMs","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T21:25:34.494112Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2501.04985"},"observation_digest":"sha256:308e9d280673b0cc117b2249b44bf29c4cccae4d1a31e5f5a02735b77c5e9813","observation_id":"11439ee7-65cf-4088-ab14-257f9a529a17","resolution":{"observed_at":"2026-08-10T21:25:34.494112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-08T22:06:38.935952Z","title":"Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.04643","last_updated":"2025-02-10T06:46:48Z","snapshot_observed_at":"2026-08-21T12:51:27.316112Z","submitted_at":"2025-02-07T04:07:36Z","title":"Confidence Elicitation: A New Attack Vector for Large Language Models","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T22:06:38.935952Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2502.04643"},"observation_digest":"sha256:74d4391408b28359de325c93f87bdbefcd592d2c6045ce2eefe9460d4179ab8c","observation_id":"ccc52258-f62b-4fa7-84cd-293a857cff19","resolution":{"observed_at":"2026-08-08T22:06:38.935952Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-16T10:59:52.396711Z","title":"arXiv preprint arXiv:2005.05909 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.16801","last_updated":"2025-08-26T03:13:51Z","snapshot_observed_at":"2026-08-22T07:18:33.023676Z","submitted_at":"2025-04-23T15:20:53Z","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-16T10:59:52.396711Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2504.16801"},"observation_digest":"sha256:661cccbec13dd9e087c38f3e8f62d5aaa70b2261ab9f0f2f4b0badc74892a065","observation_id":"d19593e3-947a-4c98-8f36-c4506b95ca03","resolution":{"observed_at":"2026-08-16T10:59:52.396711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-16T10:36:45.998864Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17723","last_updated":"2025-07-24T08:03:09Z","snapshot_observed_at":"2026-08-20T23:44:53.009005Z","submitted_at":"2025-04-24T16:36:19Z","title":"Statistical Runtime Verification for LLMs via Robustness Estimation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T10:36:45.998864Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2504.17723"},"observation_digest":"sha256:6554a1f4681f76faafac8be1ba22e6e0f78287cb7ab703fe78881b281df70ac4","observation_id":"da6430d9-597b-4cef-af04-018df6dc7457","resolution":{"observed_at":"2026-08-16T10:36:45.998864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-16T04:41:49.390654Z","title":"X., Lifland, E., Yoo, J","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.00792","last_updated":"2025-05-01T18:44:20Z","snapshot_observed_at":"2026-08-20T19:00:16.700989Z","submitted_at":"2025-05-01T18:44:20Z","title":"Improving Routing in Sparse Mixture of Experts with Graph of Tokens","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T04:41:49.390654Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2505.00792"},"observation_digest":"sha256:ebc60616750b43d7e72f6da4a4cfec10d88b36aa4e1e2224f6b125c9c9dc199b","observation_id":"8f6847ba-bca2-4b42-86d5-5839ccfc19f2","resolution":{"observed_at":"2026-08-16T04:41:49.390654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-07T12:45:19.444402Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp.arXiv preprint arXiv:2005.05909, 2020","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.23713","last_updated":"2025-05-29T17:47:36Z","snapshot_observed_at":"2026-08-20T01:41:37.092236Z","submitted_at":"2025-05-29T17:47:36Z","title":"SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:19.444402Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2505.23713"},"observation_digest":"sha256:39ba6ea24d28984000fa5b8aac1ce56a9dba012a3f72660d17475fbb8b139191","observation_id":"3d23c6e0-dd3b-4975-9538-84b8fd3bba74","resolution":{"observed_at":"2026-08-07T12:45:19.444402Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-07T12:35:21.396314Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.24341","last_updated":"2025-05-30T08:32:45Z","snapshot_observed_at":"2026-08-21T12:07:37.263041Z","submitted_at":"2025-05-30T08:32:45Z","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:21.396314Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2505.24341"},"observation_digest":"sha256:6c8c06dc08fd1918444b6dfa653e0bf00d8e75cbe842188ae65bd8c55d90bc10","observation_id":"f19981b6-7ddc-49af-af5d-ccb9b827bb9b","resolution":{"observed_at":"2026-08-07T12:35:21.396314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-07T05:21:35.071014Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.08227","last_updated":"2025-06-09T20:53:43Z","snapshot_observed_at":"2026-08-15T13:08:24.643875Z","submitted_at":"2025-06-09T20:53:43Z","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:35.071014Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2506.08227"},"observation_digest":"sha256:d4182cba8e018042be4b650900c8aedb6f4cdff6b088dc42da63c3ceffcffdbf","observation_id":"6ad48054-2851-4434-8254-b444e1fc6a33","resolution":{"observed_at":"2026-08-07T05:21:35.071014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-06T22:59:48.055868Z","title":"Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.20701","last_updated":"2025-06-25T17:59:10Z","snapshot_observed_at":"2026-08-20T12:39:55.017233Z","submitted_at":"2025-06-25T17:59:10Z","title":"Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T22:59:48.055868Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2506.20701"},"observation_digest":"sha256:3fe9cc9b0f2dc3f9dcc6925c4a5717e1f586b74eae8c769590a6fe03a6c8b6d9","observation_id":"cc92c8af-298a-4a08-9377-4d512610e210","resolution":{"observed_at":"2026-08-06T22:59:48.055868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-06T21:53:17.358520Z","title":"Christopher A","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.23123","last_updated":"2025-06-29T07:16:48Z","snapshot_observed_at":"2026-08-18T12:41:41.206813Z","submitted_at":"2025-06-29T07:16:48Z","title":"The Societal Impact of Foundation Models: Advancing Evidence-based AI Policy","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:53:17.358520Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2506.23123"},"observation_digest":"sha256:a4a35f857fa41376b529f51edc5ee2e70cbcd8d872462b5d757aa4cafec35651","observation_id":"8e07427f-0d7b-4129-ba89-fc6fc81c6cf5","resolution":{"observed_at":"2026-08-06T21:53:17.358520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-06T18:55:54.832482Z","title":"Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.06956","last_updated":"2025-07-09T15:39:17Z","snapshot_observed_at":"2026-08-18T10:58:20.807113Z","submitted_at":"2025-07-09T15:39:17Z","title":"Investigating the Robustness of Retrieval-Augmented Generation at the Query Level","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T18:55:54.832482Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2507.06956"},"observation_digest":"sha256:20d313474a7bd7f809eb5c875fdd43ea2366ab9aa312ef6c4575bf785366cb55","observation_id":"d12f18d4-36e4-477e-96fd-5040d68c2f01","resolution":{"observed_at":"2026-08-06T18:55:54.832482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-06T17:35:48.347629Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.14202","last_updated":"2025-07-14T17:41:12Z","snapshot_observed_at":"2026-08-22T02:31:42.670661Z","submitted_at":"2025-07-14T17:41:12Z","title":"PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-06T17:35:48.347629Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2507.14202"},"observation_digest":"sha256:8ef17ec17d174477ac7a56af7634a981ec46685bd6a292a9f4aa0277620ec078","observation_id":"103ae790-ec3e-4edf-bf4e-122cf26e8719","resolution":{"observed_at":"2026-08-06T17:35:48.347629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-06T15:46:44.823362Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.15067","last_updated":"2025-07-20T18:03:44Z","snapshot_observed_at":"2026-08-09T09:52:59.156741Z","submitted_at":"2025-07-20T18:03:44Z","title":"ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T15:46:44.823362Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2507.15067"},"observation_digest":"sha256:fa16d8e947ee8c233eb3d65872420d76bd64e36499f5416519c1050210c586c2","observation_id":"90d3897a-c5a1-4268-b98c-e8fea1bffea5","resolution":{"observed_at":"2026-08-06T15:46:44.823362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-15T17:50:55.719057Z","title":"arXiv:2005.05909 [cs.CL] https://arxiv.org/abs/ 2005.05909","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.21188","last_updated":"2025-07-27T16:48:53Z","snapshot_observed_at":"2026-08-20T19:32:08.726813Z","submitted_at":"2025-07-27T16:48:53Z","title":"Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T17:50:55.719057Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2507.21188"},"observation_digest":"sha256:23607dc590635e5bce5405b41b9b5234f277dee86314739ebbba6dce9ac71c8e","observation_id":"7a4597ce-244e-4700-bc9c-8f6667df236f","resolution":{"observed_at":"2026-08-15T17:50:55.719057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-06T05:32:12.214353Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2508.01605","last_updated":"2025-08-03T05:42:20Z","snapshot_observed_at":"2026-08-20T03:28:19.123172Z","submitted_at":"2025-08-03T05:42:20Z","title":"Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T05:32:12.214353Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2508.01605"},"observation_digest":"sha256:a1d081733982695b9ceef990ef4f2214a6bb5a757e757321d8245ae3f2f4b251","observation_id":"28e3c9ee-2ecf-4ca4-a0bf-7e76b20cf39e","resolution":{"observed_at":"2026-08-06T05:32:12.214353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":"2005.05909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-07-03T13:08:08.786365Z","title":"In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations","venue":null,"work_id":"14c74400-036d-491d-b0c3-76e6bf1b4fbb","year":2005},"citing_paper":{"arxiv_id":"2508.15840","last_updated":"2026-06-19T19:43:21Z","snapshot_observed_at":"2026-08-17T22:24:36.199530Z","submitted_at":"2025-08-19T17:34:25Z","title":"Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution","version":6},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T21:58:56.833425Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2508.15840"},"observation_digest":"sha256:e908688c63ad640670e87b799365ed683d171fc43e15a8e6e37cbed0ff88ad96","observation_id":"56507a9b-f66c-4a67-98de-551eaa62ab92","resolution":{"observed_at":"2026-05-18T22:01:51.970128Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-05T18:51:05.174579Z","title":"In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.15840","last_updated":"2026-06-19T19:43:21Z","snapshot_observed_at":"2026-08-17T22:24:36.199530Z","submitted_at":"2025-08-19T17:34:25Z","title":"Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution","version":7},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T18:51:05.174579Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2508.15840"},"observation_digest":"sha256:f4bd039eb4dac5206ad4ae13c3c037c21fc18fac4aeadf7b041ea2810d85ab60","observation_id":"442df1a7-ddfc-4754-b63c-9e3349473728","resolution":{"observed_at":"2026-08-05T18:51:05.174579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-05T17:14:37.108958Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp.arXiv preprint arXiv:2005.05909, 2020","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2508.18306","last_updated":"2025-08-23T02:50:55Z","snapshot_observed_at":"2026-08-14T20:23:35.152528Z","submitted_at":"2025-08-23T02:50:55Z","title":"SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:37.108958Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2508.18306"},"observation_digest":"sha256:83423f7dce5fed4dc8471a7fd25d71dd014dc7e46543193221ae74c31a3633da","observation_id":"8f6bdc07-69e0-494a-9313-7341cd0a7d43","resolution":{"observed_at":"2026-08-05T17:14:37.108958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-04T17:38:24.527887Z","title":"Textattack: A framework for adversarial attacks in natural language processing,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2509.10790","last_updated":"2025-09-13T02:52:08Z","snapshot_observed_at":"2026-08-13T16:46:54.993743Z","submitted_at":"2025-09-13T02:52:08Z","title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T17:38:24.527887Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2509.10790"},"observation_digest":"sha256:2a48030f1ded89d15ae6e4eeb035ac1d4ac7f0504c2b7c4f2a6c168e214a7c69","observation_id":"f7e92ad1-029a-45d4-b334-2615d2261f15","resolution":{"observed_at":"2026-08-04T17:38:24.527887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":"2005.05909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-07-03T13:08:08.786365Z","title":"In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations","venue":null,"work_id":"14c74400-036d-491d-b0c3-76e6bf1b4fbb","year":2005},"citing_paper":{"arxiv_id":"2606.00540","last_updated":"2026-05-30T05:14:53Z","snapshot_observed_at":"2026-08-01T17:48:34.431096Z","submitted_at":"2026-05-30T05:14:53Z","title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","version":1},"reference_index":166,"source":"pdf_text","source_observed_at":"2026-06-28T18:41:06.636352Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2606.00540"},"observation_digest":"sha256:04ff3a77eb37e4ac2f5b85e6ee7fb750d2821974a2beba080b3275a63231c8ef","observation_id":"5400241e-2231-40f9-a9f7-acb2d0a48260","resolution":{"observed_at":"2026-06-28T18:42:29.237410Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":"2005.05909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-07-03T13:08:08.786365Z","title":"In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations","venue":null,"work_id":"14c74400-036d-491d-b0c3-76e6bf1b4fbb","year":2005},"citing_paper":{"arxiv_id":"2606.11533","last_updated":"2026-06-10T00:34:04Z","snapshot_observed_at":"2026-08-15T13:35:53.203422Z","submitted_at":"2026-06-10T00:34:04Z","title":"AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-06-27T08:26:57.379418Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2606.11533"},"observation_digest":"sha256:770fe10b73b4ff7bd5fe70f0460e0e3b784b2b3402a4aa88fcfe4e661b50075b","observation_id":"d51d2cfd-145a-4336-9c8f-a180870035c0","resolution":{"observed_at":"2026-07-03T13:08:08.787613Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-01T01:26:17.518510Z","title":"arXiv preprint arXiv:2005.05909 (2020)","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.25814","last_updated":"2026-07-28T14:58:28Z","snapshot_observed_at":"2026-08-18T12:43:28.822394Z","submitted_at":"2026-07-28T14:58:28Z","title":"Evaluation of Adversarial Robustness in Arabic Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T01:26:17.518510Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2607.25814"},"observation_digest":"sha256:9fbada38fcf4fc71de0e2b29b31227728dc25af16f858c9cc0fbe06666d89b08","observation_id":"2ae21208-d47e-4b57-acfb-f091325ba0d1","resolution":{"observed_at":"2026-08-01T01:26:17.518510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-15T21:19:22.176307Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.12889","last_updated":"2026-08-13T07:12:13Z","snapshot_observed_at":"2026-08-20T19:00:16.702788Z","submitted_at":"2026-08-13T07:12:13Z","title":"Adversarial Robustness in Smishing Detection: A Comparative Analysis of Adversarial Fragility in Classical vs. Transformer-Based Detection Systems","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T21:19:22.176307Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2608.12889"},"observation_digest":"sha256:758c25739e4a0d2b57a7d0ae4f951a565f919cae30946889390c94c3b3c1aaac","observation_id":"52d01433-889e-4799-bfd2-ff7cf28c2e68","resolution":{"observed_at":"2026-08-15T21:19:22.176307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2005.05909/citation-record","integrity":"/paper/2005.05909/integrity","json":"/paper/2005.05909/citation-record.json","paper":"/paper/2005.05909"},"outbound":[],"paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T03:04:28.486504Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 31 inbound Pith citation observations for arXiv:2005.05909."}