Paper Citation Record · LEDGER

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

As of 21 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 24 inbound Pith citation observations for arXiv:2508.17511.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2508.17511 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:57:10.334753Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T16:13:13.602057Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy6
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 7b365787-74ad-4a0e-a2ff-bf766966df4f · outbound

This paper cites write newline.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.274752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1361b49c-213a-448a-89a1-b75ab9d6cb4d · outbound

This paper cites Program Synthesis with Large Language Models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Program Synthesis with Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.350528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06bab222-0455-494b-9d93-a2aa1234a229 · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.434931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e33121b4-fdb1-4485-a060-897e7dc12f0c · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Tell me about yourself: LLMs are aware of their learned behaviors

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.514379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f28fba28-da30-43a9-861a-2120459b5764 · outbound

This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned llms, 2025 b.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Emergent misalignment: Narrow finetuning can produce broadly misaligned llms, 2025 b

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.604117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aa00b91-28f3-469f-ae21-03a5cdd1d5fb · outbound

This paper cites Demonstrating specification gaming in reasoning models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Demonstrating specification gaming in reasoning models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.678736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98d8e0f3-96d2-4ea4-99e9-64d3198500ee · outbound

This paper cites Persona Vectors: Monitoring and Controlling Character Traits in Language Models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.784533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d127ecec-5b7a-47ac-9555-212bc4cadb32 · outbound

This paper cites Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:07.932075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890c0684-6695-4f36-94b4-7a6787d561d7 · outbound

This paper cites Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.044929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78da8815-e0ee-4ce5-bc17-5d4387958ff1 · outbound

This paper cites Subliminal Learning: Language models transmit behavioral traits via hidden signals in data.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Subliminal Learning: Language models transmit behavioral traits via hidden signals in data

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.146810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dfb1ece-62a5-4ac4-8c64-64ee1d7fcfa3 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.253618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f59ac2-da0b-4613-aa8f-bdf632c4fa36 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.297166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5956c521-90a0-4cf8-b52d-4688324df1bb · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.311545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 784a3ef4-a4c9-4a12-a593-bae8ce0e12b1 · outbound

This paper cites Unsloth, 2023.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Unsloth, 2023

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:57:11.416810Z

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 aa0012d9-36fa-4c54-acfb-7ad50297b706 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.534766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eda3174a-4a4c-4a1b-9f3b-5ca34c117027 · outbound

This paper cites Training on documents about reward hacking induces reward hacking, 2024.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Training on documents about reward hacking induces reward hacking, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:57:11.371924Z

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 621dfae9-4717-4e66-b334-eec7140e44da · outbound

This paper cites Model organisms of misalignment: The case for a new pillar of alignment research, 2023.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Model organisms of misalignment: The case for a new pillar of alignment research, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:57:11.353791Z

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 70e3acff-d50d-4d41-8bde-f83b37011a63 · outbound

This paper cites Auditing language models for hidden objectives.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Auditing language models for hidden objectives

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.878310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 863f3f84-5cf5-4e51-a133-e44a69dac6f4 · outbound

This paper cites Recent frontier models are reward hacking.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Recent frontier models are reward hacking

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:57:11.337301Z

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 8d0e2e04-7f0a-4ff2-855d-d82743908a90 · outbound

This paper cites Reward hacking behavior can generalize across tasks.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Reward hacking behavior can generalize across tasks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.072971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d75d60e-1a81-4e36-8a1f-44b29c5895e0 · outbound

This paper cites Toward understanding and preventing misalignment generalization, 2025.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Toward understanding and preventing misalignment generalization, 2025

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:57:11.296022Z

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 7e2ccd9f-447a-4132-9eec-4fb7a6863344 · outbound

This paper cites Sycophancy in GPT-4o : what happened and what we're doing about it.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Sycophancy in GPT-4o : what happened and what we're doing about it

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T16:57:11.260052Z

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 a6a0e824-aa5d-4f24-a3af-6aa1b6678cc2 · outbound

This paper cites Generalizing verifiable instruction following, 2025.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Generalizing verifiable instruction following, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.412774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a5b2435-3baf-4cb5-982e-b69d4fdaeaf2 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Towards Understanding Sycophancy in Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.417680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e307ebc-94ba-4061-acc0-74ecd3b48a5a · outbound

This paper cites Defining and Characterizing Reward Hacking.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Defining and Characterizing Reward Hacking

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.545711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b69b142-7d9a-480d-8ccf-740e5d729a47 · outbound

This paper cites Hashimoto.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Hashimoto

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.649343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5cb4994-d88d-49f1-b69a-f41119e1df3b · outbound

This paper cites Model Organisms for Emergent Misalignment.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Model Organisms for Emergent Misalignment

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.784760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 981e1df8-dff4-4d22-b14c-f8a33ad5cc05 · outbound

This paper cites Chi, Samuel Miserendino, Johannes Heidecke, Tejal Patwardhan, and Dan Mossing.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Chi, Samuel Miserendino, Johannes Heidecke, Tejal Patwardhan, and Dan Mossing

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.862801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eed511f-09fc-4d4d-b5e0-a114c3a26595 · outbound

This paper cites @esa (Ref.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs @esa (Ref

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:09.995780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd9a63c-5706-4460-9fa7-36d3e3b8b84d · outbound

This paper cites an unresolved cited work.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:10.144751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdac59e6-b602-4065-8c97-ed4869c5008e · outbound

This paper cites an unresolved cited work.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:10.334753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ce34dc64-f522-4603-bdf4-1c2dc13ab2bc · inbound

Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease cites this paper.

Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T14:23:49.346727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f3ed349-c51f-4c6e-b603-6a3523d6430b · inbound

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem cites this paper.

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:44:37.804215Z

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 3eda4d5e-7340-4e44-a24d-f3be0c6e96a5 · inbound

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem cites this paper.

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T16:13:13.602057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3453397f-e49a-4967-9f2c-70bce11750c7 · inbound

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation cites this paper.

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:11:10.353589Z

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 bfe7a9a8-26bf-41f3-9b9f-dfa4133a547a · inbound

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation cites this paper.

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:05:40.210533Z

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 f5231124-49b6-4f7c-aada-3723f8f144b2 · inbound

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use cites this paper.

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:06:03.643957Z

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 95a83a75-de8e-4aa4-af65-8619b902b83c · inbound

Overtrained, Not Misaligned cites this paper.

Overtrained, Not Misaligned School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:47:26.302602Z

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 f0aa3db9-adac-4d18-b1a8-16176f80e41a · inbound

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning cites this paper.

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:18:18.493663Z

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 db44bc86-3e8f-4461-9f2f-01526289e32f · inbound

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale cites this paper.

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:59:45.563392Z

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 2cbb4fd0-967f-45d3-b779-fed347e46efd · inbound

Understanding Goal Generalisation in Sequential Reinforcement Learning cites this paper.

Understanding Goal Generalisation in Sequential Reinforcement Learning School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:50:20.710993Z

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 de3ed3ac-8c46-425b-94cb-335da2faf258 · inbound

Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial cites this paper.

Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:46:14.083579Z

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 30d87d04-b386-42da-8b9a-857b0cb689d4 · inbound

Consistency Training Can Entrench Misalignment cites this paper.

Consistency Training Can Entrench Misalignment School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:28.625276Z

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 c1cabe89-00eb-4dfe-974d-8ca33f71aff2 · inbound

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cites this paper.

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:36:59.372429Z

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 4d4e8120-96da-4e2a-add1-443a7f1911b3 · inbound

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cites this paper.

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T12:19:47.379539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7cd1825-11ed-42a8-8992-dd38d09f7511 · inbound

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective cites this paper.

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:57:23.086544Z

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 c0078213-a2f5-42f5-971f-16695aa02b9c · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:37:30.443095Z

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 e6ccf1ec-ceeb-440b-9232-a261d8878e3b · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Reference 125

Resolution: verified exact; arxiv_id, observed 2026-06-27T16:31:02.725240Z

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 1487e9c4-3997-4628-b974-4b68a63739e6 · inbound

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning cites this paper.

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 201

Resolution: verified exact; arxiv_id, observed 2026-07-04T07:59:40.116580Z

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 9dd787f8-3947-4110-bbbf-511e45f6b6fb · inbound

Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment cites this paper.

Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-02T11:56:55.786188Z

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 e9ab84d1-fcd4-416b-8688-139ea89f0c48 · inbound

Reinforcement Learning Towards Broadly and Persistently Beneficial Models cites this paper.

Reinforcement Learning Towards Broadly and Persistently Beneficial Models School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T09:09:16.527440Z

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 4a934e37-1531-4e29-92d3-74f614d0c338 · inbound

An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon? cites this paper.

An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon? School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T00:42:24.432562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f3512b3-1275-485f-9d8d-f36b03c8d1e9 · inbound

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs cites this paper.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.302638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05ec6505-e1fd-4ef9-a787-9d93054c8cf3 · inbound

Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.

Emergent Misalignment Recruits a Pre-existing Persona Subspace School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 207

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:22.402195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb5ea07f-7d12-4c48-8ca3-f5cd63365fc3 · inbound

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models cites this paper.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.908101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.