{"as_of":"2026-08-19T18:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3183a82e6f11e66c1b8a3a7ccb7eff7db64c825718a00e61daf44fe3a2abb5f2","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:34:06.076571Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.00010/citation-record","integrity":"/paper/2505.00010/integrity","json":"/paper/2505.00010/citation-record.json","paper":"/paper/2505.00010"},"outbound":[{"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":"2026-08-16T11:34:05.959157Z","title":"Z., Fredrikson, M.: Universal and Trans- ferable Adversarial Attacks on Aligned Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.959157Z"},"links":{"cited_paper":"/paper/2307.15043","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:d8c745f7e182020543d754eed493b9b02834173dbad0f2bf596d2ebbed0122c0","observation_id":"aca56f2a-63f5-4fa9-8dee-7e29e1ed1235","resolution":{"observed_at":"2026-08-16T11:34:05.959157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_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},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00614","snapshot_observed_at":"2026-08-16T11:34:05.963888Z","title":"arXiv preprint arXiv:2309.00614 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.963888Z"},"links":{"cited_paper":"/paper/2309.00614","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:35c13bd278f40f17f25310291cd77ad825b38d67a2fbfc4fc64c32b05536c7fa","observation_id":"924cbc20-b39c-48b8-9e50-87e6a2d912e9","resolution":{"observed_at":"2026-08-16T11:34:05.963888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04295","last_updated":"2024-08-30T11:57:47Z","snapshot_observed_at":"2026-08-12T17:45:10.384900Z","submitted_at":"2024-07-05T06:57:30Z","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04295","snapshot_observed_at":"2026-08-16T11:34:05.967752Z","title":"arXiv preprint arXiv:2407.04295 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.967752Z"},"links":{"cited_paper":"/paper/2407.04295","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:930a3994d15b373a25a9fbe8f8721d8880168a2d3258e7b8d06611ae75e39744","observation_id":"ebdcc855-90e1-469b-925f-a8ce60ec3938","resolution":{"observed_at":"2026-08-16T11:34:05.967752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18104","last_updated":"2024-06-10T11:20:43Z","snapshot_observed_at":"2026-08-16T18:08:19.232075Z","submitted_at":"2024-02-28T06:50:14Z","title":"Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18104","snapshot_observed_at":"2026-08-16T11:34:05.971739Z","title":"arXiv preprint arXiv:2402.18104 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.971739Z"},"links":{"cited_paper":"/paper/2402.18104","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:8cd93880a5a541f7c40910260c4aa11a7f33c8b244b0099168c29a98002ff0c2","observation_id":"e20d42c4-07c8-4bfb-9e08-55bd51ca902f","resolution":{"observed_at":"2026-08-16T11:34:05.971739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01288","last_updated":"2024-10-30T12:08:42Z","snapshot_observed_at":"2026-08-16T18:08:17.585364Z","submitted_at":"2024-06-03T12:59:17Z","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01288","snapshot_observed_at":"2026-08-16T11:34:05.975360Z","title":"arXiv preprint arXiv:2406.01288 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.975360Z"},"links":{"cited_paper":"/paper/2406.01288","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:308c43de042215323ba17a6c89b8f8c1887f8402021ae21618a9189e4f22f24b","observation_id":"2dbddb2b-3dfe-485b-826c-678e3dae5b59","resolution":{"observed_at":"2026-08-16T11:34:05.975360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12173","last_updated":"2023-05-05T14:26:17Z","snapshot_observed_at":"2026-08-12T14:45:22.117576Z","submitted_at":"2023-02-23T17:14:38Z","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12173","snapshot_observed_at":"2026-08-16T11:34:05.979215Z","title":"arXiv preprint arXiv:2302.12173 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.979215Z"},"links":{"cited_paper":"/paper/2302.12173","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:34b118ce2b651a25ad0a9861229e4d8ed8ff8d5d96061f38f475e817316f186c","observation_id":"db0ddc5d-1090-43bb-bb9e-969b1f89a74c","resolution":{"observed_at":"2026-08-16T11:34:05.979215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.13916","last_updated":"2022-06-16T21:12:42Z","snapshot_observed_at":"2026-07-06T11:52:19.105210Z","submitted_at":"2021-09-28T17:59:36Z","title":"Unsolved Problems in ML Safety","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.13916","snapshot_observed_at":"2026-08-16T11:34:05.983456Z","title":"arXiv preprint arXiv:2109.13916 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.983456Z"},"links":{"cited_paper":"/paper/2109.13916","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:ba92e02ded9329a75e4c826b682b046dee01ea90a6a0b630294c22bfd42b94bc","observation_id":"2b4cf211-10a3-4eec-9740-2449eac11b1d","resolution":{"observed_at":"2026-08-16T11:34:05.983456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00898","last_updated":"2024-01-31T19:52:00Z","snapshot_observed_at":"2026-08-16T14:22:44.256192Z","submitted_at":"2024-01-31T19:52:00Z","title":"An Early Categorization of Prompt Injection Attacks on Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00898","snapshot_observed_at":"2026-08-16T11:34:05.987267Z","title":"M., Mukkamala, R","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.987267Z"},"links":{"cited_paper":"/paper/2402.00898","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:ecb81ef80d0b3b60dd19cbd22c8bc4a59c98e6f3f5b9ec0972a72931ea8a2955","observation_id":"1353cb4f-3c75-4ac0-9e60-7e3f08ddcbf8","resolution":{"observed_at":"2026-08-16T11:34:05.987267Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.16205","last_updated":"2025-06-18T02:41:56Z","snapshot_observed_at":"2026-08-16T13:31:54.315862Z","submitted_at":"2024-07-23T06:14:41Z","title":"LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.16205","snapshot_observed_at":"2026-08-16T11:34:05.990799Z","title":"arXiv preprint arXiv:2407.16205 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.990799Z"},"links":{"cited_paper":"/paper/2407.16205","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:4c6b1523e1170bd23129909b91aa97e071881b1a18b5f0a8cb02160023cf2e9f","observation_id":"a0768a78-8f61-48a5-96e8-71df50420631","resolution":{"observed_at":"2026-08-16T11:34:05.990799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.06426","last_updated":"2025-05-28T19:18:39Z","snapshot_observed_at":"2026-08-19T15:05:49.284747Z","submitted_at":"2024-11-10T11:08:28Z","title":"SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.06426","snapshot_observed_at":"2026-08-16T11:34:05.994261Z","title":"A., Shanto, M","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.994261Z"},"links":{"cited_paper":"/paper/2411.06426","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:85c697a01f24777fc4621e4c4dbffb2ce83bb4fced391e88f8477409e578987d","observation_id":"01bdb830-3ef2-4a41-afce-e0c81a7073dd","resolution":{"observed_at":"2026-08-16T11:34:05.994261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.04359","last_updated":"2021-12-08T16:09:48Z","snapshot_observed_at":"2026-08-09T15:17:43.394064Z","submitted_at":"2021-12-08T16:09:48Z","title":"Ethical and social risks of harm from Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.04359","snapshot_observed_at":"2026-08-16T11:34:05.997750Z","title":"A., Isaac, W., Legassick, S., Irving, G., Ga- briel, I.: Ethical and Social Risks of Harm from Language Models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:05.997750Z"},"links":{"cited_paper":"/paper/2112.04359","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:eccb794fa5b89d0e126e4b62975d3885bf8ef045f56ae1575f2f718f2b0d8b19","observation_id":"e4529d57-b99a-47fe-aea4-6f9e329d0434","resolution":{"observed_at":"2026-08-16T11:34:05.997750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-08-13T07:04:41.220509Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-16T11:34:06.001792Z","title":"arXiv pre- print arXiv:2201.11903 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.001792Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:37a174beda3dde6130fc25946630a64df37b798efe16377e2227a4bdc5266011","observation_id":"043939cf-7e57-43de-9de2-fa9d1e454835","resolution":{"observed_at":"2026-08-16T11:34:06.001792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11916","last_updated":"2023-01-29T05:14:17Z","snapshot_observed_at":"2026-08-13T05:54:24.242465Z","submitted_at":"2022-05-24T09:22:26Z","title":"Large Language Models are Zero-Shot Reasoners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11916","snapshot_observed_at":"2026-08-16T11:34:06.005038Z","title":"S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large Language Models are Zero- Shot Reasoners","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.005038Z"},"links":{"cited_paper":"/paper/2205.11916","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:be65f8b6d092675a8977e36bbda0142c1283cf6c1b0eb4d3a5fb868a0d40c414","observation_id":"a89b8ca8-ddcb-42ef-81fd-c64365bd755e","resolution":{"observed_at":"2026-08-16T11:34:06.005038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-08-16T01:49:22.176843Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-16T11:34:06.008645Z","title":"arXiv pre- print arXiv:2203.11171 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.008645Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:c0dfde40086a1d527e99b663b41aa444a5403b00cc777da92358a66f6e376815","observation_id":"b458719b-5979-439b-9d15-df5bb921859b","resolution":{"observed_at":"2026-08-16T11:34:06.008645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08387","last_updated":"2022-09-28T19:24:24Z","snapshot_observed_at":"2026-08-16T18:06:02.875024Z","submitted_at":"2021-10-15T21:58:03Z","title":"Generated Knowledge Prompting for Commonsense Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.08387","snapshot_observed_at":"2026-08-16T11:34:06.012569Z","title":"arXiv preprint arXiv:2110.08387 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.012569Z"},"links":{"cited_paper":"/paper/2110.08387","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:77eb8d158667ab039e2ef73af8e1a66631d3db568e006e4386a82e25fbe71ba2","observation_id":"f184ed7a-1af8-48fd-88fd-611feb04a5a1","resolution":{"observed_at":"2026-08-16T11:34:06.012569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10625","last_updated":"2023-04-16T22:08:08Z","snapshot_observed_at":"2026-08-16T05:27:41.446467Z","submitted_at":"2022-05-21T15:34:53Z","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10625","snapshot_observed_at":"2026-08-16T11:34:06.016121Z","title":"arXiv preprint arXiv:2205.10625 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.016121Z"},"links":{"cited_paper":"/paper/2205.10625","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:b3d79abb2ecb359151c91a4625b73491efdc9779f97a3aa769ba4dd457287c96","observation_id":"147e97f7-1b46-413f-9bb4-a3e04607d164","resolution":{"observed_at":"2026-08-16T11:34:06.016121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10601","last_updated":"2023-12-03T22:50:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T23:16:17Z","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10601","snapshot_observed_at":"2026-08-16T11:34:06.019948Z","title":"L., Cao, Y., Narasimhan, K.: Tree of Thoughts: Deliberate Problem Solving with Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.019948Z"},"links":{"cited_paper":"/paper/2305.10601","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:cd491fa7af42c1ef19d84b56b5468cd560729e2d9f4dfc01c84396c2512d0b15","observation_id":"2ef29112-7d1a-451a-87e6-bdb41366de1a","resolution":{"observed_at":"2026-08-16T11:34:06.019948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.15248","last_updated":"2024-07-21T19:23:45Z","snapshot_observed_at":"2026-08-16T13:32:19.670191Z","submitted_at":"2024-07-21T19:23:45Z","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.15248","snapshot_observed_at":"2026-08-16T11:34:06.023607Z","title":"arXiv preprint arXiv:2407.15248 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.023607Z"},"links":{"cited_paper":"/paper/2407.15248","citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:edf5c8415f4e75aefcc63d7525865801ce1f8ca1543d1bd88e47ea9627a0756c","observation_id":"7aaec499-8e99-47e8-ad7b-c420497d6bc5","resolution":{"observed_at":"2026-08-16T11:34:06.023607Z","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":"2026-08-16T11:34:06.027945Z","title":"-S., Kay, J., Knight, S., Martinez-Maldonado, R., Sadiq, S., Gašević, D.: Explainable Artificial Intelligence in Edu- cation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.027945Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:f1e546293d221c0aeb4c17a0b306520ca9ce60c68a337fd5ba929ad58b0c3b43","observation_id":"86bbfa5c-aa1c-4a04-a9b7-b367ef146309","resolution":{"observed_at":"2026-08-16T11:34:06.027945Z","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":"2026-08-16T11:34:06.031612Z","title":"Computers and Education: Artificial Intelligence, 5, 100152 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.031612Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:4d3ab844ab1969418e6d54fe6bded3a55544d98ee68b58900ed314db0bdcf44d","observation_id":"3ef1cc80-c4fb-48b6-abb1-b3b1b172424a","resolution":{"observed_at":"2026-08-16T11:34:06.031612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.540443Z","title":"Electronics, 14(7), 1294 (2025)","venue":null,"work_id":"f07119b0-fce2-4cd3-bbec-f7454c07a26a","year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.034686Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:007891fc969fdf667f5d6c40f3d7d53aecbc27b8f0c7956843836895c6a2f4ff","observation_id":"01662f7c-7f71-44c1-940f-cdc0ae3d16a7","resolution":{"observed_at":"2026-08-16T11:34:06.542980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.532843Z","title":"Journal of Machine Learning Research, 12, 2825–2830 (2011)","venue":null,"work_id":"471a4650-d9ee-495f-86cc-5a94301bf127","year":2011},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.038043Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:ec98de78b58e5253da76c050d92a59e005164acce2b6d37173db584ef4f3f555","observation_id":"4779acdf-bca6-4b01-9b4c-94baf8fb1eb6","resolution":{"observed_at":"2026-08-16T11:34:06.535639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.523706Z","title":"https://ba- lins.github.io/fuzzytree/index.html (accessed April 6, 2025)","venue":null,"work_id":"908e94df-a2b6-4ee4-97e2-18c9bded3b91","year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.041742Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:5e25cec1c3894de3ec407a206794467f26f6d103fa11f02a797c8ecafc75d767","observation_id":"94e59f99-b8c9-49d1-b2d6-c7f4279c99c3","resolution":{"observed_at":"2026-08-16T11:34:06.526858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.514864Z","title":null,"venue":null,"work_id":"ed2859a7-70a6-414e-b805-d0b0416f7de5","year":2014},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.044983Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:0976ec476b95f91e443eba701411a1515ca4136e08b526acdcb51762aade9e30","observation_id":"fdf9d375-67f5-4f19-bf02-30cf67aa8e98","resolution":{"observed_at":"2026-08-16T11:34:06.518134Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.503793Z","title":"-Y.: LightGBM: A Highly Efficient Gradient Boosting Decision Tree","venue":null,"work_id":"398e2cd2-f000-48d4-90d9-aa57d8ef811d","year":2017},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.047971Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:88959772db0c52ab7dfed735567ec1d7b33f824f70f8dd6b153188f39bb353db","observation_id":"0573adad-5390-48b8-ab85-60cd6f4fa33c","resolution":{"observed_at":"2026-08-16T11:34:06.507807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.051039Z","title":"Random Forests","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.051039Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:3f8b80fa4993642d0ae005266207f4b2e111a5184a6ef30c92ec35305fa20b67","observation_id":"b9cc49ef-8f09-486d-af25-40d7719429d0","resolution":{"observed_at":"2026-08-16T11:34:06.051039Z","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":"2026-08-16T11:34:06.054282Z","title":"In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794 (2016)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.054282Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:56083dad594af1a342f80cada3845022afb4d58b521207695157908582da2f2d","observation_id":"eb6874ed-51d6-48b6-b37d-167de0e726e9","resolution":{"observed_at":"2026-08-16T11:34:06.054282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.493088Z","title":"https://github.com/dmlc/xgboost (ac- cessed April 6, 2025)","venue":null,"work_id":"dd7e64d8-b4c2-47c8-ad82-96d5067ee14f","year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.057968Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:0ac859a5c97b4e1fd3de4cc74471e9bd418539dd36eca9d1ab1d00813b2a1e23","observation_id":"d7959a6b-bd04-4131-82d1-90ad2a5123ab","resolution":{"observed_at":"2026-08-16T11:34:06.496666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.482965Z","title":"-Y.: LightGBM GitHub Repository","venue":null,"work_id":"6648abd3-46ab-42b5-b8b2-1a099587d29e","year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.060863Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:d98b122acd38d37d2ad3359a10c8f9cc9d005b6ef27792905b7e1cbef44e9487","observation_id":"e58eb298-e0bb-43c6-8577-89c6f91ffa37","resolution":{"observed_at":"2026-08-16T11:34:06.486296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.472255Z","title":"Integrated Computer -Aided Engineering, 32(1), 25 –38 (2025)","venue":null,"work_id":"0191a7fa-fbea-446a-b2f0-e3715b5ec16a","year":2025},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.064015Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:54c12e9906025844ec691f8b74c30d4ad4a132ddb51702e3defe83267cb1883d","observation_id":"bbce3418-32e9-432f-a238-a9972f861b23","resolution":{"observed_at":"2026-08-16T11:34:06.476446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.463012Z","title":"A.: Fuzzy Sets","venue":null,"work_id":"cdc80f14-cf67-4f02-9844-c90d068a1ea3","year":1965},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.067134Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:6ff9420f40c91be6dd37ccd8febc0ae097bbe99d20181b9c0fd3954c3c6ff4bc","observation_id":"6e10a109-80d2-49f3-a88b-44b981394b74","resolution":{"observed_at":"2026-08-16T11:34:06.466027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.453194Z","title":null,"venue":null,"work_id":"c1232fb7-8a4d-4244-817a-13ff4709ff55","year":2015},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.070408Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:34765b2830ec55c874ae230cff76e5beeff59641c0910693f3c07b0cf23edc51","observation_id":"7aa6b4ab-8812-48c8-9579-dbc0947fe4e1","resolution":{"observed_at":"2026-08-16T11:34:06.456685Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.073577Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.073577Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:31b2af7dc35b74395593f53ed720910dfb2fcf11aae749500f939553e22d53df","observation_id":"09079ead-7dee-432c-814d-9423afc57438","resolution":{"observed_at":"2026-08-16T11:34:06.073577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:34:06.435284Z","title":"E., Hinton, G","venue":null,"work_id":"62ed3b8e-00e5-4736-b8ea-98d09c7b27e1","year":1986},"citing_paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T11:34:06.076571Z"},"links":{"citing_paper":"/paper/2505.00010"},"observation_digest":"sha256:3b02932169c5fb78eade31021081b4428b5f71fc5f5c43d298fd5a1c00f029b9","observation_id":"8ec94d38-048d-4589-9d6e-9fcbc3340733","resolution":{"observed_at":"2026-08-16T11:34:06.439802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.00010","last_updated":"2025-04-21T16:54:35Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T20:49:22.036588Z","submitted_at":"2025-04-21T16:54:35Z","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":0,"verified_fuzzy":9},"total_outbound_references":34},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2505.00010."}