Paper Citation Record · LEDGER

Misalignment from Treating Means as Ends

As of 7 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2507.10995.

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

pith.paper-citation-record.v1
2507.10995 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:34:15.255851Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

38 of 38 outbound references displayed

verified exact1
verified fuzzy29
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 88265400-60cf-49f2-811c-ecbbfbd15654 · outbound

This paper cites Faulty reward functions in the wild.

Misalignment from Treating Means as Ends Faulty reward functions in the wild

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.644297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 79375c00-6796-4b4a-af29-0df029ce93dc · outbound

This paper cites Potential-based shaping in model-based reinforcement learning.

Misalignment from Treating Means as Ends Potential-based shaping in model-based reinforcement learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.634052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9afe300b-8795-4d1f-a755-f6937a1eae89 · outbound

This paper cites Discrete dynamic programming.

Misalignment from Treating Means as Ends Discrete dynamic programming

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.624257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7fb69216-d876-4780-a825-12f87281853f · outbound

This paper cites The superintelligent will: Motivation and instrumental rationality in advanced artificial agents.

Misalignment from Treating Means as Ends The superintelligent will: Motivation and instrumental rationality in advanced artificial agents

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.614442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1dda2239-00c0-4048-afc8-c3eddabe3697 · outbound

This paper cites Deep reinforcement learning from human preferences.

Misalignment from Treating Means as Ends Deep reinforcement learning from human preferences

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:14.007127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e68bce-d562-4453-8159-dfc05d25b0db · outbound

This paper cites an unresolved cited work.

Misalignment from Treating Means as Ends Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:34:15.597861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ee0d7ebe-8c38-4f58-8b6e-871135d1b94f · outbound

This paper cites Exploration-guided reward shaping for reinforcement learning under sparse rewards.

Misalignment from Treating Means as Ends Exploration-guided reward shaping for reinforcement learning under sparse rewards

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.588281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 59a02da4-7372-4db5-be5e-a2cb6fa5455a · outbound

This paper cites Dynamic potential-based reward shaping.

Misalignment from Treating Means as Ends Dynamic potential-based reward shaping

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.577539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b7db942a-cc12-495c-bbd7-0c354d537e01 · outbound

This paper cites What is it you really want of me? generalized reward learning with biased beliefs about domain dynamics.

Misalignment from Treating Means as Ends What is it you really want of me? generalized reward learning with biased beliefs about domain dynamics

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.567489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3acafe36-0836-4621-9bd8-5d3d59776dc1 · outbound

This paper cites Reward shaping in episodic reinforcement learning.

Misalignment from Treating Means as Ends Reward shaping in episodic reinforcement learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.557064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a4264b5e-a178-477f-8c19-fd9242abc934 · outbound

This paper cites The off-switch game.

Misalignment from Treating Means as Ends The off-switch game

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:14.925169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b04838-d379-48d7-a2a2-0906e7b465d3 · outbound

This paper cites Exposure and response prevention for obsessive-compulsive disorder: A review and new directions.

Misalignment from Treating Means as Ends Exposure and response prevention for obsessive-compulsive disorder: A review and new directions

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.541323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f96126d9-8445-4a64-b98d-6a9385688096 · outbound

This paper cites Teaching with rewards and punishments: Reinforcement or communication? In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 37, 2015.

Misalignment from Treating Means as Ends Teaching with rewards and punishments: Reinforcement or communication? In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 37, 2015

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.531224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 385de4a5-9185-4930-a313-3f4e81c05f78 · outbound

This paper cites People teach with rewards and punishments as communication, not reinforcements.

Misalignment from Treating Means as Ends People teach with rewards and punishments as communication, not reinforcements

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.521675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9385e40f-fbf7-4088-b447-795c1d6b83c6 · outbound

This paper cites Horn and Charles R.

Misalignment from Treating Means as Ends Horn and Charles R

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.512021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 09d72ca4-d9c5-4a43-8820-b8070f38aa5b · outbound

This paper cites Reward learning from human preferences and demonstrations in Atari.

Misalignment from Treating Means as Ends Reward learning from human preferences and demonstrations in Atari

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.502179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 34e377bc-249d-4306-b0b4-3c007a454b7a · outbound

This paper cites Interactively shaping agents via human reinforcement: The tamer framework.

Misalignment from Treating Means as Ends Interactively shaping agents via human reinforcement: The tamer framework

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.492914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3942d4f3-4cca-4c13-a3ca-f86360ca32ce · outbound

This paper cites How humans teach agents: A new experimental perspective.

Misalignment from Treating Means as Ends How humans teach agents: A new experimental perspective

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.483473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b05217fc-f97d-452d-9eea-6474cbc25f63 · outbound

This paper cites Models of human preference for learning reward functions.

Misalignment from Treating Means as Ends Models of human preference for learning reward functions

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:15.199300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db4851c-dadd-4dbc-b68b-79336cf351f3 · outbound

This paper cites Learning optimal advantage from preferences and mistaking it for reward.

Misalignment from Treating Means as Ends Learning optimal advantage from preferences and mistaking it for reward

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.473562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cd331bdb-b089-4b25-9a86-9a209c9fd58f · outbound

This paper cites BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping.

Misalignment from Treating Means as Ends BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:34:15.299575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c0656be-52b7-4a18-9432-4a76b93da383 · outbound

This paper cites an unresolved cited work.

Misalignment from Treating Means as Ends Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:34:15.463949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6383da11-7435-4a03-bc2a-2451044abaae · outbound

This paper cites Choice between partial trajectories: Disentangling goals from beliefs, 2024.

Misalignment from Treating Means as Ends Choice between partial trajectories: Disentangling goals from beliefs, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.454002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0400189d-aec9-4f9d-8d28-b305e0bf115d · outbound

This paper cites Policy invariance under reward transformations: Theory and application to reward shaping.

Misalignment from Treating Means as Ends Policy invariance under reward transformations: Theory and application to reward shaping

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.444941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 457b866a-e7c5-48ae-bcb4-c4308c19a0ab · outbound

This paper cites Anthropic’s new AI model threatened to reveal engineer’s affair to avoid being shut down.

Misalignment from Treating Means as Ends Anthropic’s new AI model threatened to reveal engineer’s affair to avoid being shut down

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.435244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2b3f10f5-6b0a-408d-84b1-8e72cf5ce63c · outbound

This paper cites The basic AI drives.

Misalignment from Treating Means as Ends The basic AI drives

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.424662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8d5bda20-19af-46a3-a813-f9933b54f384 · outbound

This paper cites Learning to drive a bicycle using reinforcement learning and shaping.

Misalignment from Treating Means as Ends Learning to drive a bicycle using reinforcement learning and shaping

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.413722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 45e6ca2a-9107-4ec4-9254-7dea463fec9a · outbound

This paper cites AI is learning to escape human control.

Misalignment from Treating Means as Ends AI is learning to escape human control

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.402944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4e66a997-67d8-41d3-be94-1999cabb3f9e · outbound

This paper cites Human-compatible artificial intelligence, 2022.

Misalignment from Treating Means as Ends Human-compatible artificial intelligence, 2022

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.393424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae0afa82-5d18-4aab-948f-d298f630f731 · outbound

This paper cites Artificial intelligence: a modern approach.

Misalignment from Treating Means as Ends Artificial intelligence: a modern approach

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.383047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3c1f24bb-19f9-4cfa-ba51-389bb9f34d54 · outbound

This paper cites Where do rewards come from.

Misalignment from Treating Means as Ends Where do rewards come from

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.372851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 87166d99-fb94-4a85-aa04-c247f9d643e1 · outbound

This paper cites Intrinsically motivated reinforcement learning: An evolutionary perspective.

Misalignment from Treating Means as Ends Intrinsically motivated reinforcement learning: An evolutionary perspective

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:15.238058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bff7598-8344-439e-b985-d32ea35a874f · outbound

This paper cites Corrigibility.

Misalignment from Treating Means as Ends Corrigibility

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.357143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 028f26ba-7548-48ff-958d-1dcd59cf1be7 · outbound

This paper cites Reinforcement learning: An introduction, volume 1.

Misalignment from Treating Means as Ends Reinforcement learning: An introduction, volume 1

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:15.243611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f36d324-050b-43f8-8cc8-0a64e926a041 · outbound

This paper cites Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance.

Misalignment from Treating Means as Ends Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.340391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 16481d20-58c4-41ae-a253-d4e787523bb0 · outbound

This paper cites a ngberg, Mikael B \.

Misalignment from Treating Means as Ends a ngberg, Mikael B \

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.329928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 63e2764a-c98a-46d2-a69c-2090a722c3fb · outbound

This paper cites Principled methods for advising reinforcement learning agents.

Misalignment from Treating Means as Ends Principled methods for advising reinforcement learning agents

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:15.319816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f12742d6-154c-4225-adfa-8cd93a2728e0 · outbound

This paper cites Reward Shaping via Meta-Learning.

Misalignment from Treating Means as Ends Reward Shaping via Meta-Learning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:15.255851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.