{"as_of":"2026-08-08T21:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:11743d0f478d1b9cc3de85941eea70803a3d0877d732f6e3e7c4dae9e9f40549","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":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":23,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T21:55:56.833996Z","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":"2026-07-10T06:15:00.866473Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2107.06499","last_updated":"2022-03-24T19:29:45Z","snapshot_observed_at":"2026-08-05T18:30:13.997811Z","submitted_at":"2021-07-14T06:06:52Z","title":"Deduplicating Training Data Makes Language Models Better","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-05-24T13:36:55.210708Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2107.06499"},"observation_digest":"sha256:c05f96a5b9abbd7a2cfeddb4d0063220bdefbc9dca20b22710d56298ea625734","observation_id":"645a6d85-5ddb-43fd-b1f8-0d801cce792c","resolution":{"observed_at":"2026-05-24T13:39:31.665485Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2307.15043","last_updated":"2023-12-20T20:48:57Z","snapshot_observed_at":"2026-07-06T15:59:23.019044Z","submitted_at":"2023-07-27T17:49:12Z","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-24T07:42:09.112946Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2307.15043"},"observation_digest":"sha256:443386cc87370410b74c84ba9eeeaa11d904779c013251df7e2e0a6f72355f5a","observation_id":"51751e4c-a6b8-468f-8be4-42ff42147cec","resolution":{"observed_at":"2026-05-24T07:44:08.501178Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-08T21:55:56.833996Z","title":"Universal adversarial triggers for attacking and analyzing nlp,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.04679","last_updated":"2025-02-07T05:58:16Z","snapshot_observed_at":"2026-08-08T21:50:25.732611Z","submitted_at":"2025-02-07T05:58:16Z","title":"Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T21:55:56.833996Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2502.04679"},"observation_digest":"sha256:45eb27709a6aa415e746571a53828fe2c22f90c71cdd3343c68231352e4d035c","observation_id":"825360b9-5028-4b56-be78-1f2f0ccd7687","resolution":{"observed_at":"2026-08-08T21:55:56.833996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-08T11:17:01.699125Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.07987","last_updated":"2025-06-04T18:10:51Z","snapshot_observed_at":"2026-08-08T11:11:03.867295Z","submitted_at":"2025-02-11T22:07:47Z","title":"Universal Adversarial Attack on Aligned Multimodal LLMs","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T11:17:01.699125Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2502.07987"},"observation_digest":"sha256:c0e1bc7a90899c32136bb9b74e456cd70a9b1aee708bdb7829181cce881bda0f","observation_id":"d5deb967-4af0-4aae-ba2f-2045e62dfd03","resolution":{"observed_at":"2026-08-08T11:17:01.699125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-07T15:31:23.552833Z","title":"arXiv preprint arXiv:1908.07125 (2019)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.14835","last_updated":"2025-05-20T18:57:38Z","snapshot_observed_at":"2026-08-07T15:26:36.454592Z","submitted_at":"2025-05-20T18:57:38Z","title":"Robust and Efficient AI-Based Attack Recovery in Autonomous Drones","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:31:23.552833Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2505.14835"},"observation_digest":"sha256:208c2dac3aa5c351abad4f950f44728d89cf287fbecea3f2d99b981f2f1822db","observation_id":"546d9cc7-131f-4da2-9f4f-7e7b30a05d13","resolution":{"observed_at":"2026-08-07T15:31:23.552833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-07T14:00:08.447260Z","title":"Universal adversarial triggers for attacking and analyzing nlp","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.20259","last_updated":"2025-05-26T17:40:40Z","snapshot_observed_at":"2026-08-07T13:53:48.214686Z","submitted_at":"2025-05-26T17:40:40Z","title":"Lifelong Safety Alignment for Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T14:00:08.447260Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2505.20259"},"observation_digest":"sha256:e510ec4568d7504d927ec51ad1ccb1b5bc07193b39bf30fb5cd6478e6bda053d","observation_id":"3b319180-7c6c-4567-8f10-b5ce34044201","resolution":{"observed_at":"2026-08-07T14:00:08.447260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-07T14:31:48.604253Z","title":"Universal adversarial triggers for attacking and analyzing NLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21537","last_updated":"2025-05-24T09:07:13Z","snapshot_observed_at":"2026-08-08T02:37:32.325481Z","submitted_at":"2025-05-24T09:07:13Z","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","version":1},"reference_index":160,"source":"arxiv_source","source_observed_at":"2026-08-07T14:31:48.604253Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2505.21537"},"observation_digest":"sha256:5acac7a6eb10f374b5af1ddb484870ad3c35dc16cd85d98dd6fad53844114ffc","observation_id":"b60321bc-507e-4225-b546-64b0f2acdad9","resolution":{"observed_at":"2026-08-07T14:31:48.604253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-07T11:23:40.132422Z","title":"Universal adversarial triggers for attacking and analyzing nlp,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2506.02696","last_updated":"2025-06-03T09:44:28Z","snapshot_observed_at":"2026-08-07T11:15:44.312106Z","submitted_at":"2025-06-03T09:44:28Z","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:23:40.132422Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2506.02696"},"observation_digest":"sha256:dcebfd5217450e069f89ddb093a49ebdb95f0f7e657ef4e433fbb87dcc7bc804","observation_id":"45024b38-fe8e-4cd8-a652-cb0dbcefcca1","resolution":{"observed_at":"2026-08-07T11:23:40.132422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-06T22:07:05.264755Z","title":"Universal adversarial triggers for attacking and analyzing nlp.arXiv preprint arXiv:1908.07125, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2506.22666","last_updated":"2026-05-30T16:23:21Z","snapshot_observed_at":"2026-08-06T21:58:37.734178Z","submitted_at":"2025-06-27T22:22:00Z","title":"VERA: Variational Inference Framework for Jailbreaking Large Language Models","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:07:05.264755Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2506.22666"},"observation_digest":"sha256:3116ed1e8a30513b8edfd7770cf8d254dc630c2c7ce91b39cc55206e7531f493","observation_id":"29f60ec0-f4e9-486d-9abe-6d832cf5d7bb","resolution":{"observed_at":"2026-08-06T22:07:05.264755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-06T17:35:48.488605Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.14202","last_updated":"2025-07-14T17:41:12Z","snapshot_observed_at":"2026-08-08T03:22:49.699348Z","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":78,"source":"arxiv_source","source_observed_at":"2026-08-06T17:35:48.488605Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2507.14202"},"observation_digest":"sha256:18beb93d6491b34d22f8425c56fa74a276e6232a30f062d159e8474ace0abd37","observation_id":"923ae7d5-0634-43e6-9a9a-5af5f2a7d9bd","resolution":{"observed_at":"2026-08-06T17:35:48.488605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-06T15:52:56.831143Z","title":"Qiusi Zhan, Richard Fang, Henil Shalin Panchal, and Daniel Kang","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.14799","last_updated":"2025-07-20T03:10:13Z","snapshot_observed_at":"2026-08-06T23:52:08.348122Z","submitted_at":"2025-07-20T03:10:13Z","title":"Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T15:52:56.831143Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2507.14799"},"observation_digest":"sha256:6b1b574031f7591bc6af46233f6a6f710b27315db1bc84f25ba2798f5539d124","observation_id":"816c07a6-52ba-454e-b51d-8b1b1d560c77","resolution":{"observed_at":"2026-08-06T15:52:56.831143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-06T14:33:42.557179Z","title":"Andong Wang, Bo Wu, Sunli Chen, Zhenfang Chen, Haotian Guan, Wei-Ning Lee, Li Erran Li, J","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.22933","last_updated":"2025-07-24T16:27:38Z","snapshot_observed_at":"2026-08-07T10:18:49.594691Z","submitted_at":"2025-07-24T16:27:38Z","title":"Augmented Vision-Language Models: A Systematic Review","version":1},"reference_index":113,"source":"pdf_text","source_observed_at":"2026-08-06T14:33:42.557179Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2507.22933"},"observation_digest":"sha256:fb5fc4eed2b5bd29c6c1ae5628df7e693f6296b02d84ade61627a318ad0bbc8d","observation_id":"24711129-aa92-49be-a2e3-33519b8d36b1","resolution":{"observed_at":"2026-08-06T14:33:42.557179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2602.20102","last_updated":"2026-05-21T18:01:19Z","snapshot_observed_at":"2026-08-02T14:02:01.747985Z","submitted_at":"2026-02-23T18:19:46Z","title":"BarrierSteer: LLM Safety via Learning Barrier Steering","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-25T07:02:03.058731Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2602.20102"},"observation_digest":"sha256:f2ecafcc5719b67ea7b67613b22e6d53989a102695f8ba80971b8414a8e45b99","observation_id":"1dfa5b0f-5e9b-454c-911e-58edb954df70","resolution":{"observed_at":"2026-05-25T07:05:26.804202Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2604.04630","last_updated":"2026-04-06T12:29:49Z","snapshot_observed_at":"2026-07-06T22:53:33.177713Z","submitted_at":"2026-04-06T12:29:49Z","title":"Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-10T20:30:29.032353Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2604.04630"},"observation_digest":"sha256:d16115cd4d26fd696ab4139c0c898c7be2978f0adcbad80268585c86130bd763","observation_id":"cc96eaf6-a4e4-4f9d-ba4c-297631667e18","resolution":{"observed_at":"2026-05-10T21:55:49.767304Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2605.02236","last_updated":"2026-05-05T08:03:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-04T05:16:43Z","title":"Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-08T19:17:06.375875Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2605.02236"},"observation_digest":"sha256:0d7c5dd9113acee445bdcf8e626e1f8c261e9e3f6b54276d4b11d2abad1113fd","observation_id":"2762a09e-26de-49fb-a6a3-ef5784918d2a","resolution":{"observed_at":"2026-05-09T05:55:31.820741Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2605.12340","last_updated":"2026-05-29T07:49:08Z","snapshot_observed_at":"2026-08-02T07:56:41.241469Z","submitted_at":"2026-05-12T16:19:44Z","title":"Online Learning-to-Defer with Varying Experts","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-05-13T04:05:52.853863Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2605.12340"},"observation_digest":"sha256:03c0d30852cabfc7bd6950ed5189267d73f3681f8d5bed71c42d26778ee02d48","observation_id":"8eedd4cf-34dd-431f-855d-cfa4c1fa16b2","resolution":{"observed_at":"2026-05-13T04:07:13.136968Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2605.12340","last_updated":"2026-05-29T07:49:08Z","snapshot_observed_at":"2026-08-02T07:56:41.241469Z","submitted_at":"2026-05-12T16:19:44Z","title":"Online Learning-to-Defer with Varying Experts","version":2},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-05-21T08:07:35.959083Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2605.12340"},"observation_digest":"sha256:9ef801a2719684aadae18bb93fe01351101e6427fe2ac2f27288fc534a223f2f","observation_id":"6c4f2aea-6f1c-48aa-a3a0-8b86bfbd90b1","resolution":{"observed_at":"2026-05-21T08:09:51.360290Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2605.12809","last_updated":"2026-05-12T23:01:29Z","snapshot_observed_at":"2026-07-06T23:24:27.821980Z","submitted_at":"2026-05-12T23:01:29Z","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","version":1},"reference_index":205,"source":"arxiv_source","source_observed_at":"2026-05-14T20:17:01.224864Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2605.12809"},"observation_digest":"sha256:df2d71f296d68734ce864b3239e31ff1ef6ca26f11a994ca99abd7c789c40950","observation_id":"db9f0958-618b-46a4-a827-74c80e0819f2","resolution":{"observed_at":"2026-05-14T20:17:54.278529Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2605.18762","last_updated":"2026-04-10T08:26:40Z","snapshot_observed_at":"2026-08-03T10:46:28.403539Z","submitted_at":"2026-04-10T08:26:40Z","title":"ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-05-21T10:04:45.173272Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2605.18762"},"observation_digest":"sha256:9caf6b0b6db715ca1728068ee91d44bad053a6f43aa05f02156a24964ea6573a","observation_id":"02f8a46d-bd58-4d81-99ba-2c869bb3b592","resolution":{"observed_at":"2026-05-21T10:04:58.854227Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2605.26501","last_updated":"2026-05-26T03:28:28Z","snapshot_observed_at":"2026-08-06T01:03:47.103495Z","submitted_at":"2026-05-26T03:28:28Z","title":"Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T18:17:52.158294Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2605.26501"},"observation_digest":"sha256:e8e3ade7abb135f5bb79b569c3a438121ffe86117e2da1581e5264db1f30dabd","observation_id":"e26aab9f-c653-43bd-9514-be1e631b06f8","resolution":{"observed_at":"2026-06-29T18:23:50.902580Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":"1908.07125","doi":"10.48550/arxiv.1908.07125","metadata_source":"arxiv_reference","pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Universal adversarial triggers for attacking and analyz- ing nlp.arXiv:1908.07125","venue":null,"work_id":"1c27ffe0-d906-454c-8e9c-acb6779148d2","year":1908},"citing_paper":{"arxiv_id":"2606.12234","last_updated":"2026-06-10T15:42:15Z","snapshot_observed_at":"2026-08-05T00:08:40.346158Z","submitted_at":"2026-06-10T15:42:15Z","title":"On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-06-27T09:40:48.736006Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2606.12234"},"observation_digest":"sha256:360212c40afe31e7479cccc9438986d77ad80a5bbe6879e1e5f8e75285665dce","observation_id":"0fc62c5d-cb4a-4a4a-ade8-9e27ecc31e77","resolution":{"observed_at":"2026-07-03T11:18:03.177073Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-07-12T10:33:33.025490Z","title":"findings-emnlp.641/","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.30555","last_updated":"2026-07-29T04:26:46Z","snapshot_observed_at":"2026-08-04T00:28:35.757848Z","submitted_at":"2026-06-29T16:51:06Z","title":"Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T10:33:33.025490Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2606.30555"},"observation_digest":"sha256:a311213637620d55fe0d2f82fe99d527bff1d6b97cb2fab1d012d2213d898c38","observation_id":"db2b6f8e-06ef-4f6c-80a5-b82315db24f3","resolution":{"observed_at":"2026-07-12T10:33:33.025490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07125","snapshot_observed_at":"2026-08-02T09:39:08.416040Z","title":"findings-emnlp.641/","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.30555","last_updated":"2026-07-29T04:26:46Z","snapshot_observed_at":"2026-08-04T00:28:35.757848Z","submitted_at":"2026-06-29T16:51:06Z","title":"Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing","version":3},"reference_index":641,"source":"pdf_text","source_observed_at":"2026-08-02T09:39:08.416040Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2606.30555"},"observation_digest":"sha256:a2a35fbd2ea83974b54b92658523c7c64cedf15d80675f67618c068f437e5f00","observation_id":"3eac7930-200b-4736-9c78-1bedc3f74f8b","resolution":{"observed_at":"2026-08-02T09:39:08.416040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1908.07125/citation-record","integrity":"/paper/1908.07125/integrity","json":"/paper/1908.07125/citation-record.json","paper":"/paper/1908.07125"},"outbound":[],"paper":{"arxiv_id":"1908.07125","last_updated":"2021-01-03T19:58:55Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T08:15:25.894149Z","submitted_at":"2019-08-20T01:51:40Z","title":"Universal Adversarial Triggers for Attacking and Analyzing 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 23 inbound Pith citation observations for arXiv:1908.07125."}