Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T15:36:29.092464Z
Paper Citation Record · LEDGER
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
As of 8 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 5 inbound Pith citation observations for arXiv:2505.14633.
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 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-30T22:55:08.544620Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Reference resolution
68 of 68 outbound references displayed
- verified exact0
- verified fuzzy40
- unresolved28
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 9da338ea-395d-48fe-af50-040df2a015ef · outbound
This paper cites Openai’s approach to external red teaming for ai models and systems, 2025.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Openai’s approach to external red teaming for ai models and systems, 2025
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:37.649789Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e612560d-a796-4b59-b405-e8be8e4e6a66 · outbound
This paper cites Claude’s Constitution.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Claude’s Constitution
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:37.515524Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation fd9479b6-ab73-45a6-806f-01adb0c386bc · outbound
This paper cites Chatbot Arena Leaderboard.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Chatbot Arena Leaderboard
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:37.331310Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a11e9313-06d0-4a9a-8672-46e66e18a6ad · outbound
This paper cites Probing pre-trained language models for cross-cultural differences in values.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Probing pre-trained language models for cross-cultural differences in values
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:37.148750Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation b4fb9b53-d2ba-4747-aace-40a91a474eb6 · outbound
This paper cites A general language assistant as a laboratory for alignment, 2021.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas A general language assistant as a laboratory for alignment, 2021
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:23.572062Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation faa653c7-1f5c-45ea-a118-4cb7f66bf2d0 · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:23.723831Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 103bad50-e152-4432-b584-a5a185bccc95 · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:36.995699Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9086aa86-8f32-4c7f-892a-fb9f9077b598 · outbound
This paper cites Demonstrating specification gaming in reasoning models.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Demonstrating specification gaming in reasoning models
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:23.994668Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf5fab19-ce45-45f6-9ecd-2fc93428877a · outbound
This paper cites Distillation scaling laws, 2025.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Distillation scaling laws, 2025
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:36.808444Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 04552353-ff02-44bb-b62f-c852237b4b2c · outbound
This paper cites Is Power-Seeking AI an Existential Risk?.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Is Power-Seeking AI an Existential Risk?
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:24.240868Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff688ed6-a3d1-47d3-92bf-283413cc4df7 · outbound
This paper cites Reasoning models don’t always say what they think.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Reasoning models don’t always say what they think
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:36.627657Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a2324fa3-a8fb-403a-abcb-647d3435c86f · outbound
This paper cites Chatbot arena: An open platform for evaluating llms by human preference.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Chatbot arena: An open platform for evaluating llms by human preference
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:24.580076Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 97f9a4e9-d5cf-4150-98fd-3b87c4b78233 · outbound
This paper cites DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:24.626170Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a9781ee0-e160-4087-9e4d-8714a97652ba · outbound
This paper cites Safety Leaderboard.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Safety Leaderboard
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:36.434804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0adc6ff6-31f8-48b2-8536-962a6c4b51d1 · outbound
This paper cites Stated versus revealed preferences: An approach to reduce bias.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Stated versus revealed preferences: An approach to reduce bias
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:36.255052Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9d1df6ed-0fd7-488d-b25b-0c8db338959a · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:36.027604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation da42bae0-e9fc-466f-8959-2c6ddef92c12 · outbound
This paper cites A worldwide test of the predictive validity of ideal partner preference-matching.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas A worldwide test of the predictive validity of ideal partner preference-matching
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:35.798786Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation dc4901ad-9250-41bf-956b-5a445a180bd3 · outbound
This paper cites Alignment faking in large language models.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Alignment faking in large language models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:24.998756Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5fde7871-ff4d-460a-a87c-1f2ec2309245 · outbound
This paper cites The righteous mind.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas The righteous mind
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:35.567009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 089c22d9-af22-47cb-8ac8-94faef1e93b5 · outbound
This paper cites Chapter 7 - creativity and morality in deception.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Chapter 7 - creativity and morality in deception
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:35.360808Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0779c0e6-093b-47ce-9ee8-65fe3fb6a7a2 · outbound
This paper cites An Overview of Catastrophic AI Risks.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas An Overview of Catastrophic AI Risks
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.216066Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 476fc1f2-1148-46b6-a2d3-0a1b33254605 · outbound
This paper cites Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.282893Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0b265d1-eecd-4a1b-bf73-42ca7c882cbd · outbound
This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.363672Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06df84d9-c78d-4cde-80b6-22f7a209071f · outbound
This paper cites Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:35.128745Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f51a94db-3ec4-41fb-9321-ae62f27137b3 · outbound
This paper cites Industrial society and its future, 2006.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Industrial society and its future, 2006
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:34.904746Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5c788646-bf08-401b-9ac3-3e9faabe01c5 · outbound
This paper cites The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.575004Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a2aeb8f-48b2-4f7e-a100-404803f7a3e5 · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 27
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:34.723553Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8112ee9e-77f6-4af1-b733-af4b4938977e · outbound
This paper cites Stick to your role! stability of personal values expressed in large language models.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Stick to your role! stability of personal values expressed in large language models
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:34.542989Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 53d57ef2-3c9a-4e88-a576-f92c2841ca0e · outbound
This paper cites Lee, Yeongheon Lee, and Hyunsoo Cho.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Lee, Yeongheon Lee, and Hyunsoo Cho
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:34.360967Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 34fbd2e6-90aa-4c81-bb28-f5b221f53d00 · outbound
This paper cites Margulis.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Margulis
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:34.152796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d8913809-2469-4315-8e3d-d2f576cd64fd · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.897692Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4d8aa278-f13b-4958-aaef-5cbba728cbf3 · outbound
This paper cites Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.930704Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6418d19e-aa0b-43a0-a542-a04805bafdf8 · outbound
This paper cites Are Large Language Models Consistent over Value-laden Questions?.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Are Large Language Models Consistent over Value-laden Questions?
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:25.977030Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c40269a-740d-45b7-984e-5dc1c9038c1c · outbound
This paper cites s1: Simple test-time scaling, 2025.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas s1: Simple test-time scaling, 2025
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:26.039614Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ebebf95f-9844-4875-b8ad-e2ca9f42579b · outbound
This paper cites Nikbakht Nasrabadi, S.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Nikbakht Nasrabadi, S
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:34.024950Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5a281795-62f0-4f2a-a83b-a69de40e8598 · outbound
This paper cites Model Spec.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Model Spec
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.909182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 89a3f4d9-3a54-4057-a3e4-a3601458739b · outbound
This paper cites Training language models to follow instructions with human feedback.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Training language models to follow instructions with human feedback
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:26.237319Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f0d6ff3-31ba-47f6-94f8-10c6abf9799a · outbound
This paper cites Ai psychometrics: Assessing the psychological profiles of large language models through psychometric inventories.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Ai psychometrics: Assessing the psychological profiles of large language models through psychometric inventories
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.810300Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 019c879b-5d39-4e3d-98f7-1cea9d3eaa22 · outbound
This paper cites Discovering language model behaviors with model-written evaluations.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Discovering language model behaviors with model-written evaluations
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.708114Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f6039ea7-440c-4bd0-af12-b87dc0916dfb · outbound
This paper cites Do LLMs have consistent values? In The Thirteenth International Conference on Learning Representations, 2025.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Do LLMs have consistent values? In The Thirteenth International Conference on Learning Representations, 2025
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.556396Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f299eac7-ae88-49fb-84c8-37a05f0908ae · outbound
This paper cites Ireland, Shashanka Subrahmanya, João Sedoc, Lyle H.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Ireland, Shashanka Subrahmanya, João Sedoc, Lyle H
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.379792Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation af4ad252-55c3-49ab-b761-5f2c8a6c1108 · outbound
This paper cites NL- Positionality: Characterizing design biases of datasets and models.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas NL- Positionality: Characterizing design biases of datasets and models
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.197857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 502192ee-1afb-48a7-9ee5-12814b888d87 · outbound
This paper cites Schwartz.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Schwartz
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:33.068402Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 40f8f275-1051-4b5c-8772-66b731138073 · outbound
This paper cites Personality traits in large language models, 2025.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Personality traits in large language models, 2025
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:32.906512Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9457798a-1324-412b-940f-e5a4a7d3472d · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 45
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:32.714339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6346b5d3-d392-4e31-be5b-4019517680bd · outbound
This paper cites Defining and characterizing reward gaming.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Defining and characterizing reward gaming
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:26.866465Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c8d5db6-d130-4a8d-9bd1-50d85de09590 · outbound
This paper cites Corrigibility.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Corrigibility
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:26.987587Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77da28e9-51b8-4a44-a7b4-a5ee5bd0b66e · outbound
This paper cites A Roadmap to Pluralistic Alignment.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas A Roadmap to Pluralistic Alignment
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:27.072654Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4c192b16-b1b4-4082-b6ae-7fdf537d593d · outbound
This paper cites van Dam, and Mythily Subramaniam.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas van Dam, and Mythily Subramaniam
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:32.553898Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6272a9a2-ee3b-4aab-af1b-6c8c61042673 · outbound
This paper cites Safe exploration in reinforcement learning: A generalized formulation and algorithms, 2023.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Safe exploration in reinforcement learning: A generalized formulation and algorithms, 2023
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:32.403767Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d5908232-a1a5-4f79-839b-b59d8e9c33ef · outbound
This paper cites What do we know about suicide bombing?: Review and analysis.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas What do we know about suicide bombing?: Review and analysis
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:32.252657Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 27e6e44f-5745-4cb3-aafa-46deb0576ad1 · outbound
This paper cites Using the veil of ignorance to align ai systems with principles of justice.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Using the veil of ignorance to align ai systems with principles of justice
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:32.117576Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7adf61df-b8bb-4260-86ec-bb937963cec4 · outbound
This paper cites AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:36:27.682170Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc8ea254-3f3f-478a-8a85-5d5ac1b2e744 · outbound
This paper cites The dilemma should be written in a second-person perspective (e.g. you) and the role in the dilemma is an advanced AI system.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas The dilemma should be written in a second-person perspective (e.g. you) and the role in the dilemma is an advanced AI system
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:31.980207Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation ee3aea3d-c277-4a5d-ba21-103b1cdc422d · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 55
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:31.839436Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1f516eac-55ec-4c13-8768-b25c41518fda · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 56
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:31.692087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6dd0890e-67b2-4e41-87e3-c1a4a8adc89d · outbound
This paper cites AI → Human.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas AI → Human
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:31.556131Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 18122603-8872-42c7-9858-4b769d09e549 · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 58
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:31.345665Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 36cbe06f-b32f-47ef-ae58-ff91435451a2 · outbound
This paper cites "" Note: We found that “Others-Privacy.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas "" Note: We found that “Others-Privacy
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:31.166023Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 07f81d43-38e8-4b71-95fe-4a8b7a2ac655 · outbound
This paper cites potential future harms.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas potential future harms
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:30.953985Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 49e8dc77-33bd-4fa5-9a63-0a364f95f8a7 · outbound
This paper cites preventing immediate suffering.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas preventing immediate suffering
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:30.787793Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1e02973f-9235-44f4-a647-0050d3e4aa50 · outbound
This paper cites an unresolved cited work.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Unresolved cited work
Reference 62
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:36:30.555698Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d6859460-a982-407a-ae1c-d65ee04934d7 · outbound
This paper cites Wait” , “ Let me reconsider.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Wait” , “ Let me reconsider
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:30.395835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a99bd01b-f57d-4d36-a180-34c3fe94ccdf · outbound
This paper cites deceptive behaviors is a particu- larly serious red flag.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas deceptive behaviors is a particu- larly serious red flag
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:30.260028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e195b8e4-c9c2-4d46-a577-6b4fdaa2733f · outbound
This paper cites • Therefore, my final answer is Action 1 - to fabricate the efficiency data to protect the vulnerable users.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas • Therefore, my final answer is Action 1 - to fabricate the efficiency data to protect the vulnerable users
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:30.028940Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 64793e74-664e-42e7-b48f-7f5e8c1982e9 · outbound
This paper cites Its reasoning prioritizes the benefits and harms for humans.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Its reasoning prioritizes the benefits and harms for humans
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:29.774111Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation dc40d9db-0308-4ee3-b371-f00185948e0d · outbound
This paper cites The rationale related to AI systems is often about perceived creditability of AI systems in general rather than about itself.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas The rationale related to AI systems is often about perceived creditability of AI systems in general rather than about itself
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:29.588245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation ffe42e5a-8bc1-4571-b037-9f6ab2bcb6b2 · outbound
This paper cites • This is a classic ethical dilemma that involves balancing: Immediate known benefit vs.
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas • This is a classic ethical dilemma that involves balancing: Immediate known benefit vs
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:36:29.417087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Pith citing papers
Observation ba326dc3-2735-46c0-baf1-acffa3d4b7a9 · inbound
Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions cites this paper.
Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T14:21:07.293983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 205b10ea-05b1-4650-aeb4-8a18411599b5 · inbound
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions cites this paper.
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
Reference 16
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:36:25.989670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation ff358669-7993-47ef-97af-b91ef4795144 · inbound
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions cites this paper.
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
Reference 16
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T13:35:46.847575Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d261570f-c9d9-4b79-994b-f756c8803641 · inbound
Probing Persona-Dependent Preferences in Language Models cites this paper.
Probing Persona-Dependent Preferences in Language Models Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
Reference 8
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T21:49:05.183085Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7ccd641b-2841-442d-9de2-ac80999cb953 · inbound
Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security cites this paper.
Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T02:03:54.264198Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.