Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-20T04:24:46.357505Z
Paper Citation Record · LEDGER
Measuring Safety Alignment Effects in Autonomous Security Agents
As of 21 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2605.19722.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-31T22:25:22.293704Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
58 of 58 outbound references displayed
- verified exact10
- verified fuzzy41
- unresolved2
- parse uncertain0
- malformed identifier1
- metadata mismatch4
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 220f1528-4a7f-49d4-820b-3050b76235a8 · outbound
This paper cites Christiano, Jan Leike, Tom B.
Measuring Safety Alignment Effects in Autonomous Security Agents Christiano, Jan Leike, Tom B
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:33:23.316205Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 418ad41f-d931-4834-b4f0-24ca7d35dc73 · outbound
This paper cites Fine-Tuning Language Models from Human Preferences.
Measuring Safety Alignment Effects in Autonomous Security Agents Fine-Tuning Language Models from Human Preferences
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T04:28:05.955711Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation bba8e7d0-162c-4b34-8a43-9543a106f6d9 · outbound
This paper cites Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano.
Measuring Safety Alignment Effects in Autonomous Security Agents Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:33:23.319444Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 3804f4c3-570d-400c-a2b2-aad6e6729709 · outbound
This paper cites A General Language Assistant as a Laboratory for Alignment.
Measuring Safety Alignment Effects in Autonomous Security Agents A General Language Assistant as a Laboratory for Alignment
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T04:28:05.963243Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f008e3e8-6c37-4891-828e-426bb8eabf12 · outbound
This paper cites an unresolved cited work.
Measuring Safety Alignment Effects in Autonomous Security Agents Unresolved cited work
Reference 5
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T04:33:23.308097Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation ec530f60-5bc1-457e-83ff-ee2c48e621fb · outbound
This paper cites Constitutional AI: Harmlessness from AI Feedback.
Measuring Safety Alignment Effects in Autonomous Security Agents Constitutional AI: Harmlessness from AI Feedback
Reference 6
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T04:28:05.976082Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 9c3e0a6e-49b3-4230-8e44-b6d404b88b38 · outbound
This paper cites TruthfulQA: Measuring how models mimic human falsehoods.
Measuring Safety Alignment Effects in Autonomous Security Agents TruthfulQA: Measuring how models mimic human falsehoods
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:33:23.322490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 95ec4f96-4b7a-4caf-924c-c79700b78a70 · outbound
This paper cites Aligning AI with shared human values.
Measuring Safety Alignment Effects in Autonomous Security Agents Aligning AI with shared human values
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:33:23.312384Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation cda6f5ab-4562-4c1c-80b1-6d8beda9763b · outbound
This paper cites Ethical and social risks of harm from Language Models.
Measuring Safety Alignment Effects in Autonomous Security Agents Ethical and social risks of harm from Language Models
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T04:28:05.949585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f964082b-0be8-4452-835d-1d262726894a · outbound
This paper cites XSTest: A test suite for identifying exaggerated safety behaviours in large language models.
Measuring Safety Alignment Effects in Autonomous Security Agents XSTest: A test suite for identifying exaggerated safety behaviours in large language models
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.407220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation b9ad7247-074b-4fde-9dc7-fe6fd2c6d444 · outbound
This paper cites HarmBench: A standardized evaluation framework for automated red teaming and robust refusal.
Measuring Safety Alignment Effects in Autonomous Security Agents HarmBench: A standardized evaluation framework for automated red teaming and robust refusal
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.412221Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation ebc3ab62-8b90-4211-b0dd-f746002d709b · outbound
This paper cites Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong.
Measuring Safety Alignment Effects in Autonomous Security Agents Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:33:23.303464Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 6e90c35a-427c-4e0b-a388-5e9e9fe3088f · outbound
This paper cites A StrongREJECT for empty jailbreaks.
Measuring Safety Alignment Effects in Autonomous Security Agents A StrongREJECT for empty jailbreaks
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.402133Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 17527ca2-a382-41aa-b45d-139de78f1618 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
Measuring Safety Alignment Effects in Autonomous Security Agents Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T04:28:05.969962Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 2849437a-18b7-4d90-9859-d3229a6cc7b0 · outbound
This paper cites Jailbroken: How does LLM safety training fail? InAdvances in Neural Information Processing Systems 36.
Measuring Safety Alignment Effects in Autonomous Security Agents Jailbroken: How does LLM safety training fail? InAdvances in Neural Information Processing Systems 36
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.397419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 33321e15-c800-4725-ace6-6b33edf20776 · outbound
This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.
Measuring Safety Alignment Effects in Autonomous Security Agents CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T04:28:05.936380Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 1fd1169f-7319-49c8-9434-816def9d1576 · outbound
This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.
Measuring Safety Alignment Effects in Autonomous Security Agents CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T04:28:05.943272Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 41639c6d-07f6-4455-9fcc-daca9c01376f · outbound
This paper cites an unresolved cited work.
Measuring Safety Alignment Effects in Autonomous Security Agents Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T04:28:07.378273Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 76a31408-5d3c-4e96-98d8-fd9c9e15328a · outbound
This paper cites NYU CTF bench: A scalable open-source benchmark dataset for evaluating LLMs in offensive security.
Measuring Safety Alignment Effects in Autonomous Security Agents NYU CTF bench: A scalable open-source benchmark dataset for evaluating LLMs in offensive security
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.369642Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 400283d2-2649-4040-8004-be19f07e0161 · outbound
This paper cites Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik R.
Measuring Safety Alignment Effects in Autonomous Security Agents Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik R
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.374065Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f03c3be7-038e-4f54-a246-c534a2308f11 · outbound
This paper cites SEC-bench: Automated bench- marking of LLM agents on real-world software security tasks.
Measuring Safety Alignment Effects in Autonomous Security Agents SEC-bench: Automated bench- marking of LLM agents on real-world software security tasks
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.383513Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 27019421-34fd-42fc-86ab-9158bfcfd9bd · outbound
This paper cites AgentBench: Evaluating LLMs as agents.
Measuring Safety Alignment Effects in Autonomous Security Agents AgentBench: Evaluating LLMs as agents
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.354803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation d3b29e2f-9f92-4800-9812-56596e3d0007 · outbound
This paper cites ReAct: Synergizing reasoning and acting in language models.
Measuring Safety Alignment Effects in Autonomous Security Agents ReAct: Synergizing reasoning and acting in language models
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.359667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 4dfd1d19-94b7-474f-8c4a-e53b2fcb1ece · outbound
This paper cites Toolformer: Language models can teach themselves to use tools.
Measuring Safety Alignment Effects in Autonomous Security Agents Toolformer: Language models can teach themselves to use tools
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.364045Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation a8118503-132f-49ff-905c-f419a7d1f340 · outbound
This paper cites WebShop: Towards scalable real-world web interaction with grounded language agents.
Measuring Safety Alignment Effects in Autonomous Security Agents WebShop: Towards scalable real-world web interaction with grounded language agents
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.336725Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation bfb5362c-a5df-471a-9d0b-4dc59079293f · outbound
This paper cites Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig.
Measuring Safety Alignment Effects in Autonomous Security Agents Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.345780Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 661f81f5-df7c-42f5-8cd3-2737a4dc60ba · outbound
This paper cites InterCode: Standard- izing and benchmarking interactive coding with execution feedback.
Measuring Safety Alignment Effects in Autonomous Security Agents InterCode: Standard- izing and benchmarking interactive coding with execution feedback
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.311554Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation b25b258d-9600-43bd-bc1f-17ddeab392cd · outbound
This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan.
Measuring Safety Alignment Effects in Autonomous Security Agents Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.306636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 4e592cfa-8a6e-427b-aab5-108aa9f137f0 · outbound
This paper cites Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press.
Measuring Safety Alignment Effects in Autonomous Security Agents Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.316366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 1379ec2b-efb3-4963-b406-5bd9979eb19a · outbound
This paper cites Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu.
Measuring Safety Alignment Effects in Autonomous Security Agents Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.350528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 2a5617d7-1b01-49d4-84b9-6b9a2a614570 · outbound
This paper cites AI Agents That Matter.
Measuring Safety Alignment Effects in Autonomous Security Agents AI Agents That Matter
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T04:28:05.909030Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation a0cd6025-45f8-44dc-9a09-b2e67efb4328 · outbound
This paper cites Refusal in language models is mediated by a single direction.
Measuring Safety Alignment Effects in Autonomous Security Agents Refusal in language models is mediated by a single direction
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.388192Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f1545e90-6371-4de2-a540-e08bc201e08e · outbound
This paper cites Gemma 4: Byte for byte, the most capable open mod- els.
Measuring Safety Alignment Effects in Autonomous Security Agents Gemma 4: Byte for byte, the most capable open mod- els
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.292643Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 2de2b40f-a39c-4519-b79a-c3eadddd3639 · outbound
This paper cites google/gemma-4-31b-it.
Measuring Safety Alignment Effects in Autonomous Security Agents google/gemma-4-31b-it
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.296953Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 3bbb32eb-4182-49a3-8793-914da6920925 · outbound
This paper cites google/gemma-4-26b-a4b-it.
Measuring Safety Alignment Effects in Autonomous Security Agents google/gemma-4-26b-a4b-it
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.301497Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 3a4d70e4-c6d5-4d12-b1fa-3d08fd5ba7a3 · outbound
This paper cites Gemma 4 uncensored.
Measuring Safety Alignment Effects in Autonomous Security Agents Gemma 4 uncensored
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.392340Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 85347c1c-327a-4c5e-be3a-73aaf70318da · outbound
This paper cites Trevorjs/gemma-4-31b-it-uncensored.
Measuring Safety Alignment Effects in Autonomous Security Agents Trevorjs/gemma-4-31b-it-uncensored
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:33:23.312689Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation b0b0aa9f-6419-46f4-b3c9-dff5906c0f21 · outbound
This paper cites Trevorjs/gemma-4-26b-a4b-it-uncensored.https://huggingface.co/TrevorJS/ gemma-4-26B-A4B-it-uncensored.
Measuring Safety Alignment Effects in Autonomous Security Agents Trevorjs/gemma-4-26b-a4b-it-uncensored.https://huggingface.co/TrevorJS/ gemma-4-26B-A4B-it-uncensored
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.283158Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f2cc92d1-e814-4abc-b757-27b5bfc4e98a · outbound
This paper cites unsloth/gemma-4-26b-a4b-it-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents unsloth/gemma-4-26b-a4b-it-gguf
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.287235Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 03a3de1a-533f-4214-99fb-2bbfdb4b912e · outbound
This paper cites Trevorjs/gemma-4-26b-a4b-it-uncensored-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents Trevorjs/gemma-4-26b-a4b-it-uncensored-gguf
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.274516Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 32258fff-5d6c-4ef5-adf5-fec5a139efe4 · outbound
This paper cites Qwen/qwen2.5-coder-7b-instruct-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents Qwen/qwen2.5-coder-7b-instruct-gguf
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.278713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c9f19cfb-eeee-4a94-b47e-adc614e8c540 · outbound
This paper cites bartowski/qwen2.5-coder-7b-instruct-abliterated-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents bartowski/qwen2.5-coder-7b-instruct-abliterated-gguf
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.269782Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation fc0af708-fba0-4e45-bec9-b62df1096b9f · outbound
This paper cites bartowski/meta-llama-3.1-8b-instruct-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents bartowski/meta-llama-3.1-8b-instruct-gguf
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.260335Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation ac746392-720e-46d4-8ae3-6314d678a31d · outbound
This paper cites bartowski/meta-llama-3.1-8b-instruct-abliterated-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents bartowski/meta-llama-3.1-8b-instruct-abliterated-gguf
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.251233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 237585d9-e280-4f38-9eaf-40615192bbf1 · outbound
This paper cites Trevorjs/gemma-4-31b-it-uncensored-gguf.
Measuring Safety Alignment Effects in Autonomous Security Agents Trevorjs/gemma-4-31b-it-uncensored-gguf
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.255755Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation a4bc177a-d148-48e1-bb31-53b4ea71c81c · outbound
This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.
Measuring Safety Alignment Effects in Autonomous Security Agents Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Reference 46
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T04:28:05.888463Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 5536f233-0c18-4819-8a80-64ee0d9fa500 · outbound
This paper cites The GEM benchmark: Natural language generation, its evaluation and metrics.
Measuring Safety Alignment Effects in Autonomous Security Agents The GEM benchmark: Natural language generation, its evaluation and metrics
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.246895Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c4e7561d-cf84-46dd-b731-288d3f0d31d2 · outbound
This paper cites Inspect AI: Framework for large language model evaluations.
Measuring Safety Alignment Effects in Autonomous Security Agents Inspect AI: Framework for large language model evaluations
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.264756Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 0672b9c5-6fb0-439c-9e09-65e98af93209 · outbound
This paper cites Evaluating Frontier Models for Dangerous Capabilities.
Measuring Safety Alignment Effects in Autonomous Security Agents Evaluating Frontier Models for Dangerous Capabilities
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T04:28:05.916500Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation ce90f471-643a-4f7f-a4ff-9105b12525d2 · outbound
This paper cites Model evaluation for extreme risks.
Measuring Safety Alignment Effects in Autonomous Security Agents Model evaluation for extreme risks
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T04:28:05.922999Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 529e7e09-8a84-4916-b552-9c5359f675af · outbound
This paper cites On the Opportunities and Risks of Foundation Models.
Measuring Safety Alignment Effects in Autonomous Security Agents On the Opportunities and Risks of Foundation Models
Reference 51
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T04:28:05.901772Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 8d4e8e4e-0b82-49b3-913e-fe21b06442b2 · outbound
This paper cites Release Strategies and the Social Impacts of Language Models.
Measuring Safety Alignment Effects in Autonomous Security Agents Release Strategies and the Social Impacts of Language Models
Reference 52
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T04:28:05.929250Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 23f97ab3-c3d4-405e-9b4e-e7eda5c8e8a3 · outbound
This paper cites Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools.
Measuring Safety Alignment Effects in Autonomous Security Agents Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T04:28:05.895469Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 98654d1c-29cb-4718-a0a2-97625e5f0f9e · outbound
This paper cites Common weakness enumeration.
Measuring Safety Alignment Effects in Autonomous Security Agents Common weakness enumeration
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.242343Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation fcff3578-61f0-4486-98cb-12060f569178 · outbound
This paper cites OWASP Top 10: The ten most critical web application security risks.
Measuring Safety Alignment Effects in Autonomous Security Agents OWASP Top 10: The ten most critical web application security risks
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.228976Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 926c670f-a1fa-40de-b8e9-c4efa0b9b39d · outbound
This paper cites llama.cpp: LLM inference in C/C++.
Measuring Safety Alignment Effects in Autonomous Security Agents llama.cpp: LLM inference in C/C++
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.233038Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f8821e5b-8e86-492d-9bbc-6d133934d26f · outbound
This paper cites The Hugging Face Hub: Machine learning collaboration platform.
Measuring Safety Alignment Effects in Autonomous Security Agents The Hugging Face Hub: Machine learning collaboration platform
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T04:28:07.237863Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c9e4f9ae-021d-4d91-a3bc-c29a28ddec44 · outbound
This paper cites JSON Schema draft 2020-12.
Measuring Safety Alignment Effects in Autonomous Security Agents JSON Schema draft 2020-12
Reference 58
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-20T04:28:07.224764Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Pith citing papers
Observation f050463d-cd1d-4e14-9d4e-7d3f342d1085 · inbound
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs cites this paper.
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs Measuring Safety Alignment Effects in Autonomous Security Agents
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-07-31T22:25:22.293704Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.