Pith. sign in

Paper Citation Record · LEDGER

Endogenous Resistance to Activation Steering in Language Models

As of 4 August 2026, this Paper Citation Record lists 5 of 5 outbound references and 1 inbound Pith citation observation for arXiv:2602.06941.

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

pith.paper-citation-record.v1
2602.06941 v3

Coverage vector

measured 5 of 5 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:45:56.085372Z

measured 6 of 6 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-08T11:42:16.090162Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T19:31:10.451509Z

Reference resolution

5 of 5 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved4
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7c1b08fb-1a1d-445d-ab8f-9153b8f24509 · outbound

This paper cites {off_topic_subject}.

Endogenous Resistance to Activation Steering in Language Models {off_topic_subject}

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-03T03:45:56.078273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T03:45:56.078273Z digest=sha256:fb04a0b4168e597f8d9f25fd4ce9e39672adf71aac650364997a55e180a2c80b

Observation cdb35b47-fcf6-4a39-9dd7-0769ebc05aa4 · outbound

This paper cites Wait, that's not quite right.

Endogenous Resistance to Activation Steering in Language Models Wait, that's not quite right

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-03T03:45:56.081812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T03:45:56.081812Z digest=sha256:e1ce2edea4bed1aeb073faaabe12942fe7c7270cc56f84224cba2847762a2af2

Observation 20fae93a-bf15-4e3e-abd1-c893878e9fea · outbound

This paper cites {off_topic_subject}.

Endogenous Resistance to Activation Steering in Language Models {off_topic_subject}

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-03T03:45:56.085372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T03:45:56.085372Z digest=sha256:3e031e189286e85483aa9a8c02b0500a0cd2c01ccc9500908c0dcdfc1fa4e6c6

Observation a91679ce-fb38-436d-a2af-d486956cea64 · outbound

This paper cites The Llama 3 Herd of Models.

Endogenous Resistance to Activation Steering in Language Models The Llama 3 Herd of Models

Reference 2021

Resolution
malformed identifier
no resolver link, observed 2026-08-03T03:45:56.068306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T03:45:56.068306Z digest=sha256:e7dc05493e924c116266940105edd50acfe8a23a9f4ec06e872f8cba3ce10bc0

Observation 6a033e30-5e14-4279-a252-08e691c10fac · outbound

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

Endogenous Resistance to Activation Steering in Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-03T03:45:56.073494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T03:45:56.073494Z digest=sha256:37ee1119b8fb808d0e393ee2127ca45dc120e512ecf8a29ca9863a7c04a5829c

Pith citing papers

Observation e6be8d59-dd70-40dc-bd7b-823cbfee4fc5 · inbound

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes cites this paper.

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes Endogenous Resistance to Activation Steering in Language Models

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-06-08T02:03:51.771573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=arxiv_source observed=2026-05-08T11:42:16.090162Z digest=sha256:8a01dd864f779d6fc4d63a68a7ca2a6fd26ec0301ca1a311f54f96f0514a73b5