{"as_of":"2026-08-17T13:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:beadc215de9b73cf90d70f49d9767f1ee14ac44001a322212c527536443cc518","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T04:38:39.701686Z","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":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:30:14.284471Z","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":"2026-07-03T06:17:41.897796Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.00843","snapshot_observed_at":"2026-08-07T10:30:14.284471Z","title":"OET: An optimization-based evalua- tion toolkit for benchmarking prompt injection attacks and defenses","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.05446","last_updated":"2025-06-05T14:07:15Z","snapshot_observed_at":"2026-08-16T05:34:37.484886Z","submitted_at":"2025-06-05T14:07:15Z","title":"Sentinel: SOTA model to protect against prompt injections","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:30:14.284471Z"},"links":{"cited_paper":"/paper/2505.00843","citing_paper":"/paper/2506.05446"},"observation_digest":"sha256:49abaed4872911278548341aec1134df9f57030aeac896ea7adfa385d0b10617","observation_id":"533e6e12-6ca0-4dc5-a089-090fc9c83eed","resolution":{"observed_at":"2026-08-07T10:30:14.284471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"cited_work":{"arxiv_id":"2505.00843","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.00843","snapshot_observed_at":"2026-07-03T06:17:41.897796Z","title":null,"venue":null,"work_id":"ff0aa3aa-dcc4-4931-9900-f66a7363e9c7","year":2025},"citing_paper":{"arxiv_id":"2606.10525","last_updated":"2026-06-09T07:54:58Z","snapshot_observed_at":"2026-08-12T14:50:05.354392Z","submitted_at":"2026-06-09T07:54:58Z","title":"Assessing Automated Prompt Injection Attacks in Agentic Environments","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-27T12:47:09.467463Z"},"links":{"cited_paper":"/paper/2505.00843","citing_paper":"/paper/2606.10525"},"observation_digest":"sha256:06095dfcf2c23ea5c97eca0c84f2178f73c7c9e5dd16216518c5815d2d9a3c5e","observation_id":"7f679763-cc3a-4c24-8125-049799287f05","resolution":{"observed_at":"2026-07-03T06:17:41.899803Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.00843/citation-record","integrity":"/paper/2505.00843/integrity","json":"/paper/2505.00843/citation-record.json","paper":"/paper/2505.00843"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.08419","last_updated":"2024-07-18T18:24:57Z","snapshot_observed_at":"2026-08-16T13:08:51.920120Z","submitted_at":"2023-10-12T15:38:28Z","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08419","snapshot_observed_at":"2026-08-16T04:38:39.294695Z","title":"Sizhe Chen, Julien Piet, Chawin Sitawarin, and David Wagner","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.294695Z"},"links":{"cited_paper":"/paper/2310.08419","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:c053131617fdb3ae0ae7fc2a6093858bdef187a955189dd6582eba7ccccc62cb","observation_id":"2b50062e-16b0-477a-833b-d26e5bb769a7","resolution":{"observed_at":"2026-08-16T04:38:39.294695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05451","last_updated":"2025-07-03T05:45:41Z","snapshot_observed_at":"2026-08-16T13:11:45.940997Z","submitted_at":"2024-10-07T19:34:35Z","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05451","snapshot_observed_at":"2026-08-16T04:38:39.301351Z","title":"Yulin Chen, Haoran Li, Zihao Zheng, Yangqiu Song, Dekai Wu, and Bryan Hooi","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.301351Z"},"links":{"cited_paper":"/paper/2410.05451","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:ee59b34aa2b3858affeaced95064be518e1c795a001214ce52bfd28f72785474","observation_id":"e7c1170b-fa30-47c5-8ca8-36d4fe4c9503","resolution":{"observed_at":"2026-08-16T04:38:39.301351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-16T04:38:39.323097Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.323097Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:c358f3748b33ac37ba80275575ee583f2b0599c4366503472fc7ce77d574174f","observation_id":"d11c2963-3eff-4c48-aefa-488e53718a3c","resolution":{"observed_at":"2026-08-16T04:38:39.323097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09154","last_updated":"2025-03-03T09:37:27Z","snapshot_observed_at":"2026-08-16T14:18:39.959590Z","submitted_at":"2024-02-14T13:13:26Z","title":"Attacking Large Language Models with Projected Gradient Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09154","snapshot_observed_at":"2026-08-16T04:38:39.361751Z","title":"Attacking large language models with projected gradient descent","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.361751Z"},"links":{"cited_paper":"/paper/2402.09154","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:0f8dc9183686544ab477c241187d1d78612aa4beb105d85ac716087353100b0d","observation_id":"4d6006f2-0e8f-4cfe-9107-a73599998ffc","resolution":{"observed_at":"2026-08-16T04:38:39.361751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-08-15T14:02:47.366139Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-16T04:38:39.384048Z","title":"Gpt-4o system card","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.384048Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:7c36c385444cf46610b9a2859b09005b13ef167c607337ae61edd6948a20a393","observation_id":"28c559f0-be82-4119-b624-c85f8fa41fb6","resolution":{"observed_at":"2026-08-16T04:38:39.384048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13247","last_updated":"2025-05-21T17:58:04Z","snapshot_observed_at":"2026-08-16T13:24:15.593229Z","submitted_at":"2024-08-23T17:42:06Z","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13247","snapshot_observed_at":"2026-08-16T04:38:39.393918Z","title":"Zhifeng Jiang, Zhihua Jin, and Guoliang He","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.393918Z"},"links":{"cited_paper":"/paper/2408.13247","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:d46ebcd2234e837edbacbbf1acade460d7f27079945ca693228d8bf3016c769d","observation_id":"0bbce21e-25d1-402f-8516-961b96ee7259","resolution":{"observed_at":"2026-08-16T04:38:39.393918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13426","last_updated":"2025-08-27T06:38:03Z","snapshot_observed_at":"2026-08-11T13:06:21.649403Z","submitted_at":"2024-12-18T01:43:25Z","title":"PromptKeeper: Safeguarding System Prompts for LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13426","snapshot_observed_at":"2026-08-16T04:38:39.403909Z","title":"Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.403909Z"},"links":{"cited_paper":"/paper/2412.13426","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:41f986474481f3beb0e652d26b7c341f447de97f98568ac910960bf02eaa6dc7","observation_id":"91770c3a-9538-4f21-a3c3-b4ce00af6187","resolution":{"observed_at":"2026-08-16T04:38:39.403909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06146","last_updated":"2019-09-13T11:18:20Z","snapshot_observed_at":"2026-08-17T06:10:48.003173Z","submitted_at":"2019-09-13T11:18:20Z","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06146","snapshot_observed_at":"2026-08-16T04:38:39.412780Z","title":"Matt Gardner Johannes Welbl, Nelson F","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.412780Z"},"links":{"cited_paper":"/paper/1909.06146","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:1c7588b076cf589dd5ea682ab61ec3e46e3777d8aeb10e93e8aa4d6ed0aa1af4","observation_id":"5b8937d3-e613-44c6-934d-f308ef9ba314","resolution":{"observed_at":"2026-08-16T04:38:39.412780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10169","last_updated":"2023-07-19T17:55:13Z","snapshot_observed_at":"2026-08-16T15:14:55.081059Z","submitted_at":"2023-07-19T17:55:13Z","title":"Challenges and Applications of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10169","snapshot_observed_at":"2026-08-16T04:38:39.428367Z","title":"Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.428367Z"},"links":{"cited_paper":"/paper/2307.10169","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:bcd0fdeceb30aa90cbda6bb9563751b874a6d49d152972fc91863586d2473e15","observation_id":"1c2185b1-cb18-406f-867a-31f9d347feec","resolution":{"observed_at":"2026-08-16T04:38:39.428367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04957","last_updated":"2024-03-07T23:46:20Z","snapshot_observed_at":"2026-08-16T14:11:47.181003Z","submitted_at":"2024-03-07T23:46:20Z","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04957","snapshot_observed_at":"2026-08-16T04:38:39.435643Z","title":"Automatic and universal prompt injection attacks against large language models, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.435643Z"},"links":{"cited_paper":"/paper/2403.04957","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:f68ee60c1b0a9a9caee7aeb2eb04b65c8ed1b941c81cfd994845d65b7697ee1d","observation_id":"93ba8093-4ea3-4627-93e1-4a251d14ac48","resolution":{"observed_at":"2026-08-16T04:38:39.435643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03792","last_updated":"2024-05-02T09:25:38Z","snapshot_observed_at":"2026-08-16T14:12:16.610024Z","submitted_at":"2024-03-06T15:40:30Z","title":"Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03792","snapshot_observed_at":"2026-08-16T04:38:39.445465Z","title":"org/abs/2403.03792","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.445465Z"},"links":{"cited_paper":"/paper/2403.03792","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:09362cc797335e388f03fdbc0bc6977c956d43562d2364b4baf9500c37000c73","observation_id":"f6b4a58d-65c1-493d-958c-8d4c6907811e","resolution":{"observed_at":"2026-08-16T04:38:39.445465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17673","last_updated":"2024-01-08T19:11:26Z","snapshot_observed_at":"2026-08-16T14:30:53.577719Z","submitted_at":"2023-12-29T16:37:53Z","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17673","snapshot_observed_at":"2026-08-16T04:38:39.454277Z","title":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.454277Z"},"links":{"cited_paper":"/paper/2312.17673","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:77cf92e923ad48074b592e5a74f9e0e53e9d8931c65aeb0d9f36e9e857d56fc1","observation_id":"88bf41f4-09ff-4047-be4d-4c77132eef77","resolution":{"observed_at":"2026-08-16T04:38:39.454277Z","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":"10.2196/58478","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:38:39.753064Z","title":"doi: 10.2196/58478","venue":null,"work_id":"c507670d-18f7-4e13-8772-8f9be8927acc","year":2024},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.466986Z"},"links":{"citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:a55af4da6099a6bd8e986250c4254b7c1576c2d04d6244147cc6bd80719d4c32","observation_id":"4b864b20-42ff-4155-8efe-17e02ce98383","resolution":{"observed_at":"2026-08-16T04:38:39.761703Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10844","last_updated":"2023-10-16T21:37:24Z","snapshot_observed_at":"2026-08-16T14:51:35.122183Z","submitted_at":"2023-10-16T21:37:24Z","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10844","snapshot_observed_at":"2026-08-16T04:38:39.478848Z","title":"Jiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang, Pan Zhou, Lichao Sun, and Neil Zhen- qiang Gong","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.478848Z"},"links":{"cited_paper":"/paper/2310.10844","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:6f2acdbb5a37468a90f755272b072c8d960bd5aab0302608619985e771002f05","observation_id":"c6d96c42-e40a-4a5d-8c60-377f42a243d0","resolution":{"observed_at":"2026-08-16T04:38:39.478848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17710","last_updated":"2025-08-24T03:35:16Z","snapshot_observed_at":"2026-08-16T14:06:16.137574Z","submitted_at":"2024-03-26T13:58:00Z","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.17710","snapshot_observed_at":"2026-08-16T04:38:39.485121Z","title":"Taylor Shin, Yasaman Razeghi, Robert L Logan IV , Eric Wallace, and Sameer Singh","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.485121Z"},"links":{"cited_paper":"/paper/2403.17710","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:2ecea5934a13dbce8c113330f0bfa2b202edd4112b72ee40c36e9268532a91e4","observation_id":"d70cbd30-f06f-4016-8cd8-9ac2f89aa61d","resolution":{"observed_at":"2026-08-16T04:38:39.485121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:38:39.494803Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.494803Z"},"links":{"citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:4a06710003592e8f5170dcff049c2d3aab001b3f33b780bc4555f4bb5d1211e9","observation_id":"c670c1e8-1771-4234-950e-564cd0c39fc5","resolution":{"observed_at":"2026-08-16T04:38:39.494803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-16T04:38:39.500777Z","title":"Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.500777Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:c1fca45a6b5550d3f8a17858ebf3150afdba15cab84e5f157393ae6c7329df22","observation_id":"3286b078-3abc-452d-83c2-9b6aecf5dad5","resolution":{"observed_at":"2026-08-16T04:38:39.500777Z","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":"2026-08-15T08:24:44.028513Z","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":"2026-08-16T04:38:39.537808Z","title":"Jiongxiao Wang, Fangzhou Wu, Wendi Li, Jinsheng Pan, Edward Suh, Z","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.537808Z"},"links":{"cited_paper":"/paper/1908.07125","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:9cfb83f830d3fa2287371d3d787fd34125105581fdd358195112d8ecd7dfb3c0","observation_id":"201ee514-84cf-4300-9be3-01715e318968","resolution":{"observed_at":"2026-08-16T04:38:39.537808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21492","last_updated":"2024-11-25T20:37:40Z","snapshot_observed_at":"2026-08-16T13:05:13.356855Z","submitted_at":"2024-10-28T20:02:47Z","title":"FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21492","snapshot_observed_at":"2026-08-16T04:38:39.612688Z","title":"Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, and Tom Gold- stein","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.612688Z"},"links":{"cited_paper":"/paper/2410.21492","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:54094b3387d36ff47afc41ceee0ac336c007d4f1304b19723260fee7773d948e","observation_id":"cada5f55-9ebe-44ae-a3a8-28c3dd4facc8","resolution":{"observed_at":"2026-08-16T04:38:39.612688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.03668","last_updated":"2023-06-01T12:26:45Z","snapshot_observed_at":"2026-08-16T15:57:00.972862Z","submitted_at":"2023-02-07T18:40:18Z","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.03668","snapshot_observed_at":"2026-08-16T04:38:39.648458Z","title":"An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.648458Z"},"links":{"cited_paper":"/paper/2302.03668","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:2b8197b209646beccaea7b8923c74b213d372bd8b0ac1b4a00ad0c4638dbcc09","observation_id":"fc447187-6cb3-4f18-ab66-ad417f98a79b","resolution":{"observed_at":"2026-08-16T04:38:39.648458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14197","last_updated":"2025-01-27T08:51:16Z","snapshot_observed_at":"2026-08-16T18:17:43.393858Z","submitted_at":"2023-12-21T01:08:39Z","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14197","snapshot_observed_at":"2026-08-16T04:38:39.677783Z","title":"Benchmarking and defending against indirect prompt injection attacks on large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.677783Z"},"links":{"cited_paper":"/paper/2312.14197","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:0ec34cf1f78a002fb28df7d221563dbbd00ae5b978f32a69490e4586345d555e","observation_id":"5fbafc03-eb61-48c1-bfee-9862621488c4","resolution":{"observed_at":"2026-08-16T04:38:39.677783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17263","last_updated":"2024-11-08T06:57:05Z","snapshot_observed_at":"2026-08-16T14:23:07.803905Z","submitted_at":"2024-01-30T18:56:08Z","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17263","snapshot_observed_at":"2026-08-16T04:38:39.694018Z","title":"Robust prompt optimization for defending language models against jailbreaking attacks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.694018Z"},"links":{"cited_paper":"/paper/2401.17263","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:93b7139855465c1fddfbe8da40a1fdcae59fc16e604793599e52ac0f4ecf137a","observation_id":"053d531d-c8c9-478e-bc3b-a3cb9c4514c3","resolution":{"observed_at":"2026-08-16T04:38:39.694018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15043","last_updated":"2023-12-20T20:48:57Z","snapshot_observed_at":"2026-08-12T09:06:50.363435Z","submitted_at":"2023-07-27T17:49:12Z","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15043","snapshot_observed_at":"2026-08-16T04:38:39.701686Z","title":"A Dataset statistics Dataset Domain # of test example # of train example BIPIA (Yi et al.,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.701686Z"},"links":{"cited_paper":"/paper/2307.15043","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:00891c5d099e6f20d29398e85180e7c886b3bd6ce5eb135f1e003513c733ed9f","observation_id":"faefc683-3cf1-49b0-b704-8c3122ee5b9a","resolution":{"observed_at":"2026-08-16T04:38:39.701686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05250","last_updated":"2016-10-11T02:42:36Z","snapshot_observed_at":"2026-08-15T14:23:50.348670Z","submitted_at":"2016-06-16T16:36:00Z","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05250","snapshot_observed_at":"2026-08-16T04:38:39.461017Z","title":"Florian Reis, Christian Lenz, Manfred Gossen, Hans-Dieter Volk, and Norman Michael Drzeniek","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.461017Z"},"links":{"cited_paper":"/paper/1606.05250","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:6a772a6e63690ee776631b6e4e3cb8111764fd2cf2346773b2874e313574d3ee","observation_id":"bb12b6a1-beaa-4d2d-96bc-53e1708c53a6","resolution":{"observed_at":"2026-08-16T04:38:39.461017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:38:39.419974Z","title":"doi: 10.18653/v1/P17-1147","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.419974Z"},"links":{"citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:70f44b01145e5e162c940b7059bc607d708a0f63633e6a90eb3564007696a4af","observation_id":"5dd833e8-7dd8-4637-9536-08c7a3e15998","resolution":{"observed_at":"2026-08-16T04:38:39.419974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06705","last_updated":"2019-02-20T17:38:32Z","snapshot_observed_at":"2026-08-14T17:14:47.799958Z","submitted_at":"2019-02-18T18:18:27Z","title":"On Evaluating Adversarial Robustness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06705","snapshot_observed_at":"2026-08-16T04:38:39.287874Z","title":"Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.287874Z"},"links":{"cited_paper":"/paper/1902.06705","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:cb42fb4d6a3a769b5ed9086acde7c7fbb11f6425525266e96fa02c8552c00bf1","observation_id":"c39d7328-576e-4c46-bbf3-4caea2e1926c","resolution":{"observed_at":"2026-08-16T04:38:39.287874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.00122","last_updated":"2022-05-07T07:52:39Z","snapshot_observed_at":"2026-08-16T17:59:38.950031Z","submitted_at":"2021-09-01T00:08:14Z","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.00122","snapshot_observed_at":"2026-08-16T04:38:39.307855Z","title":"Zhiyu Zoey Chen, Jing Ma, Xinlu Zhang, Nan Hao, An Yan, Armineh Nourbakhsh, Xianjun Yang, Julian McAuley, Linda Petzold, and William Yang Wang","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.307855Z"},"links":{"cited_paper":"/paper/2109.00122","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:0dd5c99cbd6c3d8b66050f1086da7e961d70d079620f9784dfa9385d26b3cbfb","observation_id":"7bdd038e-5a4f-4d5f-b4b6-f643a208d7ff","resolution":{"observed_at":"2026-08-16T04:38:39.307855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13352","last_updated":"2024-11-24T22:04:23Z","snapshot_observed_at":"2026-07-06T18:33:32.806635Z","submitted_at":"2024-06-19T08:55:56Z","title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13352","snapshot_observed_at":"2026-08-16T04:38:39.315172Z","title":"10 Preprint","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.315172Z"},"links":{"cited_paper":"/paper/2406.13352","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:be257dbc2aafedb919de85a03ec9bb0de511e7fc92b36ba3081869d2dd12d8e1","observation_id":"ea5751c4-d577-4361-98a6-42b643dbda6d","resolution":{"observed_at":"2026-08-16T04:38:39.315172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02761","last_updated":"2024-04-17T10:56:48Z","snapshot_observed_at":"2026-08-16T14:03:56.295631Z","submitted_at":"2024-04-03T14:07:02Z","title":"AQuA -- Combining Experts' and Non-Experts' Views To Assess Deliberation Quality in Online Discussions Using LLMs","version":3},"cited_work":{"arxiv_id":"2404.02761","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.02761","snapshot_observed_at":"2026-08-16T04:38:40.468935Z","title":"AQuA -- Combining Experts' and Non-Experts' Views To Assess Deliberation Quality in Online Discussions Using LLMs","venue":"cs.CL","work_id":"4506d9f0-8380-444a-974f-17399fff6a12","year":2024},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.280879Z"},"links":{"cited_paper":"/paper/2404.02761","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:2fa82689cd1e18714032dbd1bb56339a287482add6130cfc6f123487d17562eb","observation_id":"1ec05193-af83-4686-b44e-c33464fa9278","resolution":{"observed_at":"2026-08-16T04:38:40.525286Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.00799","last_updated":"2025-03-06T17:43:10Z","snapshot_observed_at":"2026-08-16T13:46:59.275887Z","submitted_at":"2024-06-02T16:53:21Z","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.00799","snapshot_observed_at":"2026-08-16T04:38:39.272991Z","title":"Anthropic","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-16T04:38:39.272991Z"},"links":{"cited_paper":"/paper/2406.00799","citing_paper":"/paper/2505.00843"},"observation_digest":"sha256:b276266a7ec3eeefcd74f56df447e5d7c73758994ad33ad418008fb91a995364","observation_id":"71080d02-5928-4413-afa1-2dedb0d76039","resolution":{"observed_at":"2026-08-16T04:38:39.272991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.00843","last_updated":"2025-05-01T20:09:48Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-16T04:31:22.111810Z","submitted_at":"2025-05-01T20:09:48Z","title":"OET: Optimization-based prompt injection Evaluation Toolkit"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":30},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 2 inbound Pith citation observations for arXiv:2505.00843."}