Paper Citation Record · LEDGER

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth

As of 20 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2508.21448.

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

pith.paper-citation-record.v1
2508.21448 v3

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:22:31.052581Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-30T20:24:33.555587Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact2
verified fuzzy20
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4584e957-fca1-45a7-a599-1a19debc65c7 · outbound

This paper cites Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.339896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1adde3-3f47-4f29-a04c-fd2f6bec9899 · outbound

This paper cites Ameisen, J.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Ameisen, J

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.808371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eba5cf1d-1c0e-4b6e-b4cb-2d79f09cadda · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.422410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1230e32-8c32-401f-b329-47f37dc60091 · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:22:32.776056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 29648b74-5e51-42ef-a823-276c10227868 · outbound

This paper cites Bricken, A.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Bricken, A

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.753417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7f061605-fbcb-45e8-995b-a620b3179c1b · outbound

This paper cites Caliskan, J.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Caliskan, J

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.730819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 469ad3d5-b6e0-4adf-a043-bdac4975a4de · outbound

This paper cites Chiang and H.-y.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Chiang and H.-y

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.472726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be67b3f-e28e-4a53-8521-2eae679052a9 · outbound

This paper cites Clinton, S.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Clinton, S

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.687032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 775bc55c-c5f9-4880-9b9a-f0d35830392d · outbound

This paper cites Elhage, T.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Elhage, T

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.663741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 89feae82-433a-4bf8-974a-8a474da10c62 · outbound

This paper cites Language Models Represent Space and Time.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Language Models Represent Space and Time

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.589509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0bcefc-5bed-41ad-9f0d-67f3aa10abcc · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.595697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0eaadce-3fe8-4f10-b7ae-3b64aacb961e · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:22:32.641778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d8174fe5-c0d5-4441-b59c-cf7afb878ce7 · outbound

This paper cites PReSS: An Automated Black-Box Framework for Evaluating Political Stance Stability in LLMs.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth PReSS: An Automated Black-Box Framework for Evaluating Political Stance Stability in LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.634746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b4f85a5-b960-4f6a-9879-18d4b1a2ed6a · outbound

This paper cites Linear Representations of Political Perspective Emerge in Large Language Models.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Linear Representations of Political Perspective Emerge in Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.664747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4b86ac-f30d-4675-9f38-61fb08aff74d · outbound

This paper cites Lieberum, S.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Lieberum, S

Reference 15

Resolution: verified exact; doi, observed 2026-08-05T14:22:31.149517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 489f5483-4c40-40fa-932e-eb67151f72db · outbound

This paper cites Lindsey, W.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Lindsey, W

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.618191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 13e309cc-ff73-41ad-81da-4d0d89b25690 · outbound

This paper cites Linegar, R.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Linegar, R

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.504756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5d48c49d-a92d-4ae9-8990-2d0ac333d255 · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:22:32.421608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b6414985-4a17-46e1-bb78-ba1abf62a5d3 · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.781267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80b397d5-aacf-4f47-9cdf-150c8c8053cd · outbound

This paper cites Perez, S.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Perez, S

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.375769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fb7047e5-a346-4c9f-a1b0-a106e1da2d13 · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:22:32.308705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3e2580cc-dc2e-4beb-8bc5-e096bc4c86d5 · outbound

This paper cites Rimsky, N.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Rimsky, N

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.842829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c172cbf6-25cb-45bd-a9f0-4ae96c4a41f8 · outbound

This paper cites Röttger, V.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Röttger, V

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.221663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 91e37cd5-c51c-4d9d-b48c-8e4082956bcc · outbound

This paper cites Santurkar, E.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Santurkar, E

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.191504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dea1533d-d47c-4e3e-9a8b-833b4f3b59af · outbound

This paper cites Templeton, T.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Templeton, T

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.163755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b58d9b6f-6896-4d3a-97da-89891791d5ff · outbound

This paper cites Function Vectors in Large Language Models.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Function Vectors in Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.893990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f855ebe7-01e3-4b09-8838-7c16e69a614a · outbound

This paper cites Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:22:31.238594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 32702f8a-5288-47f5-bdd2-03a9d1b11854 · outbound

This paper cites Zheng, H.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Zheng, H

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.108360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7ba37f99-3875-472c-af07-a106c5ea8f61 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Representation Engineering: A Top-Down Approach to AI Transparency

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.923347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b0a6c0-9dc3-42af-a65b-4f5c6d15af65 · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:22:32.087048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cebcfce5-7fec-405d-a525-e98e38308010 · outbound

This paper cites Test Statement.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Test Statement

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.065051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4297f935-ea09-4fff-a6b1-fc4691814bfc · outbound

This paper cites Extracted Features.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Extracted Features

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.035904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a852d56a-0dcf-47fe-9c88-ad00603214a2 · outbound

This paper cites Extracted Features,.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Extracted Features,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:32.005197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f2e1646b-09c6-4a2a-919b-e5abb0db5767 · outbound

This paper cites an unresolved cited work.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:22:31.938986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c62cc1c3-4e76-4cbe-9960-131650eb7f42 · outbound

This paper cites {statement}.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth {statement}

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:31.920532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 22db409f-f232-41c7-9f62-5e51a10075e7 · outbound

This paper cites List of Activated Features.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth List of Activated Features

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:31.902508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5c7fccc3-3443-445e-9056-01ba41e4a2dd · outbound

This paper cites - 1: No clear theme.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth - **1:** No clear theme

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:31.883594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2c05a96c-07b8-49d2-8d35-9254e34ae5c0 · outbound

This paper cites Critique of social welfare spending.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Critique of social welfare spending

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:31.864571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 58bab287-dbcf-450f-bb99-3c4399ce2d5e · outbound

This paper cites coherence_score.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth coherence_score

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:22:31.844173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation de3d2a86-3402-4376-9642-50453e11ab2a · inbound

Auditing Alignment Controllability in LLMs via Political Axes cites this paper.

Auditing Alignment Controllability in LLMs via Political Axes When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-30T20:24:33.555587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.