Paper Citation Record · LEDGER

Cheap Reward Hacking Detection

As of 16 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2606.08893.

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

pith.paper-citation-record.v1
2606.08893 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T17:21:10.240399Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact6
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b98d42d3-42e0-4dc5-b116-2cbe51c41ca6 · outbound

This paper cites Concrete Problems in AI Safety.

Cheap Reward Hacking Detection Concrete Problems in AI Safety

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:17:29.187103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f6c44add-2e91-4fe2-bed6-c673b284f936 · outbound

This paper cites The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

Cheap Reward Hacking Detection The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:17:29.183546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 75304bcd-3933-46db-a0bb-907d47025a69 · outbound

This paper cites Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective.

Cheap Reward Hacking Detection Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c636e4-01cc-494a-bd20-a951750d9980 · outbound

This paper cites Bisimulation metrics for continuous Markov decision processes.SIAM Journal on Computing, 40(6):1662–1714, 2011.

Cheap Reward Hacking Detection Bisimulation metrics for continuous Markov decision processes.SIAM Journal on Computing, 40(6):1662–1714, 2011

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd2434e-3a9e-4f52-bce5-0ab395094a7d · outbound

This paper cites Density-based clustering based on hierarchical density estimates.

Cheap Reward Hacking Detection Density-based clustering based on hierarchical density estimates

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df62f231-477d-40c4-8ffe-f23000abefd9 · outbound

This paper cites Attention is all you need.Advances in Neural Information Processing Systems, 30, 2017.

Cheap Reward Hacking Detection Attention is all you need.Advances in Neural Information Processing Systems, 30, 2017

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a308ce9-e430-4ec5-9104-14a2540bed16 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Cheap Reward Hacking Detection UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:17:29.178304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 311741cf-968a-4359-826b-21266dbd64a1 · outbound

This paper cites SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization.

Cheap Reward Hacking Detection SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6548c4b7-cd22-4814-bec6-1667cfdc27e0 · outbound

This paper cites FreeLB: Enhanced Adversarial Training for Natural Language Understanding.

Cheap Reward Hacking Detection FreeLB: Enhanced Adversarial Training for Natural Language Understanding

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:17:29.181042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7e5d8476-de37-433c-a6cd-cfa907876a1f · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Cheap Reward Hacking Detection A simple framework for contrastive learning of visual representations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a2af24e-cfda-4ac2-b784-81dff15a4a67 · outbound

This paper cites Defining and characterizing reward gaming.Advances in Neural Information Processing Systems, 35: 9460–9471, 2022.

Cheap Reward Hacking Detection Defining and characterizing reward gaming.Advances in Neural Information Processing Systems, 35: 9460–9471, 2022

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 038e4a77-d0d3-4382-910e-df59295d96a7 · outbound

This paper cites Specification gaming: The flip side of AI ingenuity.DeepMind Blog, 2020.

Cheap Reward Hacking Detection Specification gaming: The flip side of AI ingenuity.DeepMind Blog, 2020

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5f902d-6ae9-49ea-9ed0-625d913bfc38 · outbound

This paper cites Programming as theory building.Microprocessing and Microprogramming, 15(5): 253–261, 1985.

Cheap Reward Hacking Detection Programming as theory building.Microprocessing and Microprogramming, 15(5): 253–261, 1985

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b89209f8-608c-4713-859f-45358207db56 · outbound

This paper cites Categorizing Variants of Goodhart's Law.

Cheap Reward Hacking Detection Categorizing Variants of Goodhart's Law

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:17:29.175446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 443cbe0c-506b-4760-8ced-f122b6570d5e · outbound

This paper cites Towards understanding sycophancy in language models.

Cheap Reward Hacking Detection Towards understanding sycophancy in language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc3b7ddc-d012-4c3e-89f0-82089c723d66 · outbound

This paper cites Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories.

Cheap Reward Hacking Detection Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:17:29.170778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 639a4d60-33d8-451a-a12a-3787297e5964 · outbound

This paper cites MICo: Improved representations via sampling-based state similarity for Markov decision processes.

Cheap Reward Hacking Detection MICo: Improved representations via sampling-based state similarity for Markov decision processes

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a837e36-267a-4c60-b80e-1eb9aa0e2e2f · outbound

This paper cites Sliced and Radon Wasserstein barycenters of measures.Journal of Mathematical Imaging and Vision, 51(1): 22–45, 2015.

Cheap Reward Hacking Detection Sliced and Radon Wasserstein barycenters of measures.Journal of Mathematical Imaging and Vision, 51(1): 22–45, 2015

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T17:21:10.240399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.