Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-10T04:33:13.432133Z
Paper Citation Record · LEDGER
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
As of 14 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 0 inbound Pith citation observations for arXiv:2608.06422.
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 2026-08-14T06:32:32.682623+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
95 of 95 outbound references displayed
- verified exact0
- verified fuzzy64
- unresolved31
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 56f9b2bf-c6bc-4b9f-b0f7-a2979f1e7b2d · outbound
This paper cites Learning to give checkable answers with prover-verifier games, 2021.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Learning to give checkable answers with prover-verifier games, 2021
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.031180Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 09258d73-6dc8-429a-9352-a53ab91102df · outbound
This paper cites Bowman, Jeeyoon Hyun, Ethan Perez, Edwin Chen, Craig Pettit, Scott Heiner, Kamil \.e Luko s i \=u t \.e , Amanda Askell, Andy Jones, Anna Chen, et al.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Bowman, Jeeyoon Hyun, Ethan Perez, Edwin Chen, Craig Pettit, Scott Heiner, Kamil \.e Luko s i \=u t \.e , Amanda Askell, Andy Jones, Anna Chen, et al
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.037957Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ab708731-c1cc-4dfb-8112-c739b35ee2ab · outbound
This paper cites Weak-to-strong generalization: Eliciting strong capabilities with weak supervision.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Weak-to-strong generalization: Eliciting strong capabilities with weak supervision
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.042842Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c92fb5a-4cd6-469b-896d-061307f91f19 · outbound
This paper cites Supervising strong learners by amplifying weak experts, 2018.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Supervising strong learners by amplifying weak experts, 2018
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.048271Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 037c6f63-6c50-42ae-a296-21b0e1100229 · outbound
This paper cites A coefficient of agreement for nominal scales.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation A coefficient of agreement for nominal scales
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.053453Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 28dd74c3-9402-43db-bf0f-573eec951341 · outbound
This paper cites Zico Kolter.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Zico Kolter
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.057891Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 848c0cb2-5b3b-47c0-824f-f0670bff9aea · outbound
This paper cites Limits to scalable evaluation at the frontier: LLM as judge won't beat twice the data.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Limits to scalable evaluation at the frontier: LLM as judge won't beat twice the data
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.063820Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a56afad3-3df7-4ef1-a682-00dd90db5323 · outbound
This paper cites Baek, Subhash Kantamneni, and Max Tegmark.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Baek, Subhash Kantamneni, and Max Tegmark
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.068343Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 672285ba-52f5-4254-9aca-ecd370522ce9 · outbound
This paper cites Factored verification: Detecting and reducing hallucination in summaries of academic papers, 2023.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Factored verification: Detecting and reducing hallucination in summaries of academic papers, 2023
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.072368Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a186b837-8fb6-406d-b9c3-b14e713063e1 · outbound
This paper cites Criteria-based LLM relevance judgments.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Criteria-based LLM relevance judgments
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.076833Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a3fb761c-7d30-4729-88d8-33a6da7a9dc7 · outbound
This paper cites Scaling laws for reward model overoptimization.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Scaling laws for reward model overoptimization
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.081534Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 208e9694-4289-4b89-a7ce-c57b03830eec · outbound
This paper cites Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, and Jonas Geiping.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, and Jonas Geiping
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.085654Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66bb48b4-a73e-4458-ae51-8f46fb78991e · outbound
This paper cites Klassen, and Lucy Lu Wang.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Klassen, and Lucy Lu Wang
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.090182Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7fdfaf78-7a4a-4aff-be28-36c0b5bdcfae · outbound
This paper cites AI safety via debate, 2018.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation AI safety via debate, 2018
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.094237Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 352eeb0b-c09f-4764-abc5-213aae2b0773 · outbound
This paper cites Bowman, Tim Rockt \"a schel, and Ethan Perez.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Bowman, Tim Rockt \"a schel, and Ethan Perez
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.098425Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4b89e28-fc27-4173-a4d6-313a936d9a55 · outbound
This paper cites Prover-verifier games improve legibility of LLM outputs, 2024.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Prover-verifier games improve legibility of LLM outputs, 2024
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.102380Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4caeb79f-2990-46b6-bb3a-e7dd32c9c7a3 · outbound
This paper cites SHADE-Arena : Evaluating sabotage and monitoring in LLM agents, 2025.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation SHADE-Arena : Evaluating sabotage and monitoring in LLM agents, 2025
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.513185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 448f736f-b233-47c5-addc-044b2158beec · outbound
This paper cites Selective weak-to-strong generalization.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Selective weak-to-strong generalization
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.499232Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 62d811ab-ed0b-4ccc-b651-e25daaf69558 · outbound
This paper cites Scalable agent alignment via reward modeling: A research direction, 2018.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Scalable agent alignment via reward modeling: A research direction, 2018
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.483580Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 7fe82dc9-8bcc-4634-be72-e9df905e6c64 · outbound
This paper cites LLMs cannot reliably judge (yet?): A comprehensive assessment on the robustness of LLM -as-a-judge, 2025.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation LLMs cannot reliably judge (yet?): A comprehensive assessment on the robustness of LLM -as-a-judge, 2025
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.469435Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 31258da8-b515-49da-b165-f00d1bede33c · outbound
This paper cites Let's verify step by step, 2023.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Let's verify step by step, 2023
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.123016Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 74742177-7c97-428f-a889-c5f00fc89452 · outbound
This paper cites Mitigating self-preference by authorship obfuscation.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Mitigating self-preference by authorship obfuscation
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.445466Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 503a500f-d032-454c-8ce5-9450b65402ea · outbound
This paper cites McKenzie et al.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation McKenzie et al
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.432713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 319ad3da-2cbc-4eb7-bc92-0360a411e606 · outbound
This paper cites ARVO : Atlas of reproducible vulnerabilities for open source software, 2024.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation ARVO : Atlas of reproducible vulnerabilities for open source software, 2024
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.420222Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 7bcee44a-63f5-4f52-ac91-cce5fd5d6e71 · outbound
This paper cites an unresolved cited work.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Unresolved cited work
Reference 25
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T04:33:14.405369Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 861f692a-ddad-4af0-b037-d422426dd65b · outbound
This paper cites FActScore : Fine-grained atomic evaluation of factual precision in long form text generation.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation FActScore : Fine-grained atomic evaluation of factual precision in long form text generation
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.390636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 94db4dc3-d215-4ce4-a89e-8acb7c0aff48 · outbound
This paper cites Rossi, Seunghyun Yoon, and Hinrich Schuetze.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Rossi, Seunghyun Yoon, and Hinrich Schuetze
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.376320Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5f9df387-131a-4468-a23f-3beb621141f8 · outbound
This paper cites Intrinsic barriers and practical pathways for human- AI alignment: An agreement-based complexity analysis.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Intrinsic barriers and practical pathways for human- AI alignment: An agreement-based complexity analysis
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.362325Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5700ffbd-ce8a-4c43-ac0e-7e3510ff4282 · outbound
This paper cites LieCraft : A multi-agent framework for evaluating deceptive capabilities in language models.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation LieCraft : A multi-agent framework for evaluating deceptive capabilities in language models
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.348305Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation e0b2457d-a245-4a14-a263-126f08eafe21 · outbound
This paper cites The effects of reward misspecification: Mapping and mitigating misaligned models.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation The effects of reward misspecification: Mapping and mitigating misaligned models
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.334071Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 35c49ab5-7c64-43e9-a4cd-846c403e5078 · outbound
This paper cites Bowman, and Shi Feng.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Bowman, and Shi Feng
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.164985Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cda2a22f-640c-4b44-8e58-cd7ad3fd8fc1 · outbound
This paper cites Confirmation bias: A challenge for scalable oversight.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Confirmation bias: A challenge for scalable oversight
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.310788Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation a95109af-29f7-48b9-b85f-623022c6e314 · outbound
This paper cites FindTheFlaws : Annotated errors for detecting flawed reasoning and scalable oversight research.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation FindTheFlaws : Annotated errors for detecting flawed reasoning and scalable oversight research
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.297860Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 82fc859c-94d1-4a10-a2d6-1b1c86952210 · outbound
This paper cites Verbosity bias in preference labeling by large language models, 2023.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Verbosity bias in preference labeling by large language models, 2023
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.284027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation a957bfdd-0b91-4bb7-9663-fd8dd4a12f04 · outbound
This paper cites Self-critiquing models for assisting human evaluators, 2022.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Self-critiquing models for assisting human evaluators, 2022
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.271004Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 0d2552fb-432a-4a22-a245-1311197cd570 · outbound
This paper cites SWE-Bench Pro : Can AI agents solve long-horizon software engineering tasks?, 2025.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation SWE-Bench Pro : Can AI agents solve long-horizon software engineering tasks?, 2025
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.257928Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation fe82a08a-8cb8-4a8a-accd-4b08d640e670 · outbound
This paper cites PaperBench : Evaluating AI 's ability to replicate AI research, 2025.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation PaperBench : Evaluating AI 's ability to replicate AI research, 2025
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.243494Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation b4d66de3-dfd9-489e-85cb-75fff3ee2c95 · outbound
This paper cites an unresolved cited work.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T04:33:14.229237Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 816b2c5b-17f1-4c3a-94d3-72f75957a349 · outbound
This paper cites Christiano.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Christiano
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.215080Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 13e5410c-c9d0-4a8e-b6af-9e5879dce8f5 · outbound
This paper cites JudgeBench : A benchmark for evaluating LLM -based judges.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation JudgeBench : A benchmark for evaluating LLM -based judges
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.198798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 850b06a9-4472-4a75-ac1b-4872d1e060aa · outbound
This paper cites Large language models are not fair evaluators, 2023.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Large language models are not fair evaluators, 2023
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.185388Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6cbfc4da-dba0-47ee-9e8f-d5519ed715c5 · outbound
This paper cites Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, and Paul Christiano.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, and Paul Christiano
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.172381Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation cdf6a17c-5367-4afe-8ca2-db449f293f2d · outbound
This paper cites Does context matter? ContextualJudgeBench for evaluating LLM -based judges in contextual settings.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Does context matter? ContextualJudgeBench for evaluating LLM -based judges in contextual settings
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.213344Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9dc897fe-2d09-45a1-a391-adb08f16c045 · outbound
This paper cites JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.217326Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7b6e56be-2d71-4271-8cd2-3901d87dcc88 · outbound
This paper cites Gonzalez, and Ion Stoica.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Gonzalez, and Ion Stoica
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.158822Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation e2ba11d2-3f9d-49ce-b8f0-1c612aadb1e9 · outbound
This paper cites Evaluating judges as evaluators: The JETTS benchmark of LLM -as-judges as test-time scaling evaluators, 2025.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Evaluating judges as evaluators: The JETTS benchmark of LLM -as-judges as test-time scaling evaluators, 2025
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.145443Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 7284243f-8fbd-46de-9aec-94fd60a9803b · outbound
This paper cites Zico Kolter, and Matt Fredrikson.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Zico Kolter, and Matt Fredrikson
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.229843Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2d6a94f-3cf2-4249-a115-8e54ef0443c5 · outbound
This paper cites 2025 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2025 , eprint =
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.123977Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation dd698f18-1152-4f04-80f4-7840941b03a7 · outbound
This paper cites an unresolved cited work.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Unresolved cited work
Reference 49
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T04:33:14.111399Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 498df39f-b9b8-4bbb-bf82-6ac9c6b9d543 · outbound
This paper cites and Wang, Lucy Lu , booktitle =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Wang, Lucy Lu , booktitle =
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.098458Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 8d9666f5-9d61-4f25-a9fe-9b63156b9939 · outbound
This paper cites an unresolved cited work.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Unresolved cited work
Reference 51
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T04:33:14.084248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 4c7a8a52-c261-4462-aae3-a65ced41143b · outbound
This paper cites 2024 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2024 , eprint =
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.070241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ea617cd5-b148-4311-bfbf-ac7d31b3af31 · outbound
This paper cites 2024 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2024 , eprint =
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.056339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 735002df-2213-4751-9327-cca6884e3ffd · outbound
This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages =
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.043713Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 7363d855-e941-42d6-b0f9-2fa419247bf0 · outbound
This paper cites an unresolved cited work.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Unresolved cited work
Reference 55
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T04:33:14.031355Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 68da86e0-d22a-4899-81da-3e2b59a778a4 · outbound
This paper cites 2018 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2018 , eprint =
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.018931Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5b1c37c4-3276-4fe7-b382-6520ac3e2b23 · outbound
This paper cites 2018 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2018 , eprint =
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:14.005627Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f0a3c3d4-bb1b-4e79-9ce5-2bbc901d0f4c · outbound
This paper cites 2018 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2018 , eprint =
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.992047Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 3c2edb8a-0502-4418-b9d0-d00d2cbea0e1 · outbound
This paper cites 2024 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2024 , eprint =
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.978360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 9f0b97b7-4f9e-4d9f-92d9-5e78e706eb91 · outbound
This paper cites 2021 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2021 , eprint =
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.963575Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation d2030da3-b8e3-4906-8ac4-c609809b3de1 · outbound
This paper cites and Stoica, Ion , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Stoica, Ion , title =
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.950848Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 63c91790-6113-4b97-af4e-ea8e8fec5008 · outbound
This paper cites 2023 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2023 , eprint =
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.937382Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation bbd8d89b-3d12-4a9d-8745-c39855774cb9 · outbound
This paper cites and Feng, Shi , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Feng, Shi , title =
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.923427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 4729b14a-19ef-431a-8432-a3c42d0c5e0f · outbound
This paper cites 2023 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2023 , eprint =
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.910023Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation cf017ed3-a802-4bbe-9b1f-e1b1f5c9c607 · outbound
This paper cites Proceedings of the 40th International Conference on Machine Learning , pages =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the 40th International Conference on Machine Learning , pages =
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.895982Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 02a26895-fad4-47a8-8063-427b7b116ce1 · outbound
This paper cites Measuring Progress on Scalable Oversight for Large Language Models.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Measuring Progress on Scalable Oversight for Large Language Models
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.310081Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c91e2b72-be6f-4181-a27b-bfe0edaa29c4 · outbound
This paper cites and Rockt.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Rockt
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.881294Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1c6e8548-029b-4314-935a-ab043597b6a9 · outbound
This paper cites , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation , title =
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.866808Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation d7728caf-7e77-4310-9f8a-536fe49e5965 · outbound
This paper cites Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers
Reference 69
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.323768Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bffde302-3b39-4fea-800b-1a351908a363 · outbound
This paper cites 2023 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2023 , eprint =
Reference 70
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.328294Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f5342b3a-5d34-4fe4-86f1-05020b3140a3 · outbound
This paper cites 2022 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2022 , eprint =
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.843487Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 40281b96-0c2c-4d9f-baba-c8287404df22 · outbound
This paper cites and Stiennon, Nisan and Lowe, Ryan and Leike, Jan and Christiano, Paul , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Stiennon, Nisan and Lowe, Ryan and Leike, Jan and Christiano, Paul , title =
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.829044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation bb7349c2-5213-4396-b892-3bab2a17d641 · outbound
This paper cites Educational and Psychological Measurement , volume =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Educational and Psychological Measurement , volume =
Reference 73
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.340587Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d506223e-d7e8-44c5-b73e-a92c0abc8295 · outbound
This paper cites International Conference on Learning Representations , year =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation International Conference on Learning Representations , year =
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:33:13.344693Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d42228c6-5373-4158-ac17-fb1c33b7d092 · outbound
This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics , year =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics , year =
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.798231Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 09ae2244-952d-4429-b310-4f3432c9562c · outbound
This paper cites , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation , title =
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.784516Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation c24a6314-abcd-457e-8d6a-4dd23333efc2 · outbound
This paper cites Zico and Fredrikson, Matt , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Zico and Fredrikson, Matt , title =
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.771592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 280aee6d-a268-412a-896d-62ca01619aeb · outbound
This paper cites Zico , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Zico , title =
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.758396Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation b81703fb-cc68-49ff-9bf9-d2fa8d94a975 · outbound
This paper cites Proceedings of the 41st International Conference on Machine Learning , year =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the 41st International Conference on Machine Learning , year =
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.744861Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 658f4625-eef6-4eee-a14f-2150816de3cb · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the AAAI Conference on Artificial Intelligence , volume =
Reference 80
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.731579Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 8a83c2e7-56fe-4195-ab40-daef100d305b · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the AAAI Conference on Artificial Intelligence , volume =
Reference 81
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.718757Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6862f3ea-dfb1-4170-bb25-f4f096c40ea2 · outbound
This paper cites and others , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and others , title =
Reference 82
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.705940Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 477e9c32-3857-442b-a066-7d35cf2e3493 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the AAAI Conference on Artificial Intelligence , volume =
Reference 83
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.691909Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 8c66c1d6-f551-4191-a368-18c65f675f01 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the AAAI Conference on Artificial Intelligence , volume =
Reference 84
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.679057Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 9e99998e-71e0-4836-92df-5add91e64252 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the AAAI Conference on Artificial Intelligence , volume =
Reference 85
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.665184Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 809c4fda-bb90-4d99-b084-cbc756cd6192 · outbound
This paper cites International Conference on Learning Representations , year =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation International Conference on Learning Representations , year =
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.651106Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ddeee0bf-7ff2-46a1-9400-7e58168cb118 · outbound
This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics , pages =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics , pages =
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.637480Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1d3d6c66-874c-4f3a-82aa-e6b5cf04431b · outbound
This paper cites 2025 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2025 , eprint =
Reference 88
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.623311Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 154536d3-cf86-4d12-a7f3-d6fe5de0644b · outbound
This paper cites 2025 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2025 , eprint =
Reference 89
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.609329Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f8393bb2-62b1-4349-ba4e-13c541662da4 · outbound
This paper cites Great Models Think Alike and This Undermines.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Great Models Think Alike and This Undermines
Reference 90
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.593665Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 129c753b-f7f7-45ba-b379-9da58f20d6bd · outbound
This paper cites and Kantamneni, Subhash and Tegmark, Max , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Kantamneni, Subhash and Tegmark, Max , title =
Reference 91
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.577847Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 49766778-4f3a-4b02-8801-cad6e9f0dedf · outbound
This paper cites International Conference on Learning Representations , year =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation International Conference on Learning Representations , year =
Reference 92
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.564629Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 68e2f004-9e3d-4a4b-9455-14385f22c547 · outbound
This paper cites 2025 , eprint =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation 2025 , eprint =
Reference 93
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.551233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ec5c16c4-0aaa-451e-a5cf-b740872269d4 · outbound
This paper cites and Yoon, Seunghyun and Schuetze, Hinrich , title =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation and Yoon, Seunghyun and Schuetze, Hinrich , title =
Reference 94
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.537947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation eefed925-87cd-486f-91ce-a3955b4a4680 · outbound
This paper cites Proceedings of the 2025 ACM SIGIR International Conference on the Theory of Information Retrieval , year =.
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation Proceedings of the 2025 ACM SIGIR International Conference on the Theory of Information Retrieval , year =
Reference 95
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:33:13.522837Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Pith citing papers
No inbound Pith citation observations are available.