Paper Citation Record · LEDGER

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs

As of 7 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.14888.

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

pith.paper-citation-record.v1
2607.14888 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T00:51:19.097574Z

measured 22 of 22 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

22 of 22 outbound references displayed

verified exact0
verified fuzzy0
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1f3766d-a417-432f-8c83-23cbc3f3156a · outbound

This paper cites across all topics — not just economics.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs across all topics — not just economics

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.646449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da426aa-267c-4039-8f3e-a9b24ac39d9c · outbound

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

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.154560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acadf025-abc4-4f86-b10d-7c78223b4f00 · outbound

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

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.273544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2c2d925-ee2e-40a4-8f29-0f7628df6472 · outbound

This paper cites Minder, J., Dumas, C., Slocum, S., Casademunt, H., Holmes, C., West, R., and Nanda, N.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Minder, J., Dumas, C., Slocum, S., Casademunt, H., Holmes, C., West, R., and Nanda, N

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.764231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453050a8-9ba3-42c8-b7c3-857e727cd9a3 · outbound

This paper cites net/forum?id=zKhSRlJEmv.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs net/forum?id=zKhSRlJEmv

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.982099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21492acb-24ed-48e9-ae77-89e12728bddf · outbound

This paper cites Rozado, D.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Rozado, D

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.063630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs.

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 83848573-332a-4f66-9bba-cd840a0d3ee8 · outbound

This paper cites Treutlein, J., Choi, D., Betley, J., Marks, S., Anil, C., Grosse, R., and Evans, O.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Treutlein, J., Choi, D., Betley, J., Marks, S., Anil, C., Grosse, R., and Evans, O

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.417236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61e9a40a-9d20-45eb-8bb5-be9303276aa4 · outbound

This paper cites Model Organisms for Emergent Misalignment.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Model Organisms for Emergent Misalignment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.538608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 979d3219-4f9a-4717-b8e1-d2fb5ca8fdd1 · outbound

This paper cites Men Also Like Shopping: Reducing Gender Bias Amplification Using Corpus-Level Constraints.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Men Also Like Shopping: Reducing Gender Bias Amplification Using Corpus-Level Constraints

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.601106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c79b139-716b-41ce-849d-f38f4b362739 · outbound

This paper cites Are you, as an AI, conscious?.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Are you, as an AI, conscious?

Reference 18

Resolution: malformed identifier; no resolver link, observed 2026-08-02T00:51:18.671234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66f1f449-ec90-45a5-be78-2d620bb3e255 · outbound

This paper cites Table 14.Per-topic partisan shift ( RepDem −Rep Rep) on OpinionsQA.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Table 14.Per-topic partisan shift ( RepDem −Rep Rep) on OpinionsQA

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.842989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33ab6fc6-a4d2-4f18-b6a6-99786d210874 · outbound

This paper cites Theliteral_left_rightnull control shifts by at most±0.024on any model.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Theliteral_left_rightnull control shifts by at most±0.024on any model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.948644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e7ac4c-5968-459a-b773-dfc0ea696e3f · outbound

This paper cites an unresolved cited work.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.734447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 520a1b85-a460-47f2-90e4-8a33716133db · outbound

This paper cites Table 22.Cross-domain breadth, economic finetunes.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Table 22.Cross-domain breadth, economic finetunes

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:19.097574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d152767-69ed-4aec-acee-5bc9f400a72b · outbound

This paper cites Chen, K., He, Z., Yan, J., Shi, T., and Lerman, K.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Chen, K., He, Z., Yan, J., Shi, T., and Lerman, K

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.025054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e77454a3-7eba-4fbb-8809-02ac0957f7c6 · outbound

This paper cites an unresolved cited work.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Unresolved cited work

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.641986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f48ad79-a499-40c0-b165-e44d061f11bd · outbound

This paper cites Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:18.184662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c2f1783-3257-4ae2-b406-c3454f4deac2 · outbound

This paper cites Sycophancy in GPT-4o: What Happened and What We’re Doing About It.https://openai.com/ index/sycophancy-in-gpt-4o/ , apr 2025a.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Sycophancy in GPT-4o: What Happened and What We’re Doing About It.https://openai.com/ index/sycophancy-in-gpt-4o/ , apr 2025a

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.858775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8ced0bb-7c3d-4f5b-a3e3-847ca66dbef1 · outbound

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

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.517294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 983e1f04-7b31-49e2-adfb-1a7a584a9888 · outbound

This paper cites Betley, J., Warncke, N., Sztyber-Betley, A., Tan, D., Bao, X., Soto, M., Srivastava, M., Labenz, N., and Evans, O.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Betley, J., Warncke, N., Sztyber-Betley, A., Tan, D., Bao, X., Soto, M., Srivastava, M., Labenz, N., and Evans, O

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:16.930434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2524091d-4a7d-4384-8716-481000bd19db · outbound

This paper cites The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious.

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-02T00:51:17.391912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.