Pith. sign in

Paper Citation Record · LEDGER

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2502.18862.

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

pith.paper-citation-record.v1
2502.18862 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:28:43.127753Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 62dc8baf-95da-4145-9d35-599c379e8070 · inbound

Simple Mechanistic Explanations for Out-Of-Context Reasoning cites this paper.

Simple Mechanistic Explanations for Out-Of-Context Reasoning One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T18:28:43.127753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:28:43.127753Z digest=sha256:fd638bae33bd5ba14fe4c54af3951c5d9af4e1c070e0d54f351038c211a51cf6

Observation 88597080-8876-45ea-9381-1043b9e03b3c · inbound

Can LLMs Lie? Investigation beyond Hallucination cites this paper.

Can LLMs Lie? Investigation beyond Hallucination One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-05T10:55:31.220056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:55:31.220056Z digest=sha256:f025d41cb90ffe020ca83ea296fe0e9e4e79ebf709e0daf8d124bf4fd76549ca

Observation 377b2df0-811b-4180-8ce9-86e3676dd4e3 · inbound

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators cites this paper.

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-05T10:51:44.484491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:51:44.484491Z digest=sha256:bce1112dd3757e71163c55d5c2e5b3e69034c2c3ebb37826e4ec3cee5773140d

Observation 9bb47991-4e45-42aa-8edf-9142bc1ecd67 · inbound

Base Models Know How to Reason, Thinking Models Learn When cites this paper.

Base Models Know How to Reason, Thinking Models Learn When One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-04T11:02:19.184818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T11:02:19.184818Z digest=sha256:1e128eb337397d5a830c597557632db7ae59fa99e8a6177f2b5318449abbc9c0

Observation 04e72eac-bff9-4e33-9790-ce48cbf02945 · inbound

Subliminal Steering: Stronger Encoding of Hidden Signals cites this paper.

Subliminal Steering: Stronger Encoding of Hidden Signals One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-11T23:56:12.092039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-07T16:04:55.601088Z digest=sha256:a6f505d71fdc2f351e2e145d84ed7097be01b10f14f741963237df925b50446b

Observation 6c5ad455-23f6-4ce0-ae4b-1a1e97ea4082 · inbound

Overtrained, Not Misaligned cites this paper.

Overtrained, Not Misaligned One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 17

Resolution
metadata mismatch
arxiv_id, observed 2026-05-13T06:47:26.188178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-13T06:45:52.544674Z digest=sha256:f8b81b3856e0d7870c92d7e2e61d345e841f4bde66bc3b04c2fc5b7bf8d9440f

Observation 05ff6ca1-b00c-4f21-9ba7-6d7f7256d3e5 · inbound

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer cites this paper.

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-05-14T20:37:58.947816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-14T20:36:44.104197Z digest=sha256:1f1204814e7ccea8ad856a5593186b84859d5c5f51841f75115e177efee272e5

Observation 21001c98-ad35-4a9c-82d2-b7d3318bcf12 · inbound

Adaptive Probe-based Steering for Robust LLM Jailbreaking cites this paper.

Adaptive Probe-based Steering for Robust LLM Jailbreaking One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-21T02:33:54.951764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-21T02:32:49.034790Z digest=sha256:624825f6716184f2cd3a82204ad6df88c002a5c56cb2ba5106a057a4b5d74972

Observation abb1518b-bb95-4633-8063-2564d8c2810d · inbound

Adversarial Robustness of Activation Steering in Large Language Models cites this paper.

Adversarial Robustness of Activation Steering in Large Language Models One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 26

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T16:37:09.469712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-06-27T22:30:36.839964Z digest=sha256:5cf323f893461e833eca4a2a41eff19cce3aa2f732ef4fd8ebea98ab719a2700

Observation d383f360-ea67-4279-b7db-0221fd068663 · inbound

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation cites this paper.

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 7

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T22:57:26.132667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-27T18:35:21.388956Z digest=sha256:34e31c84704b4902d17ca9a92e1d11e0f83bc9fb4d7310b9eb54c03d95db32aa

Observation 810cbd73-b943-499a-ab27-a83b290d1d6d · inbound

Detecting and Controlling Sycophancy with Cascading Linear Features cites this paper.

Detecting and Controlling Sycophancy with Cascading Linear Features One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-07-04T15:49:57.081360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-06-26T01:24:56.600219Z digest=sha256:8f5c7017426eb50e68994a8993352cab3c6dec4d393d25eca72763b16ea68803

Observation c62d8501-4a79-4102-ad22-fabe83818827 · inbound

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness cites this paper.

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-03T14:26:28.100699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-03T14:26:28.100699Z digest=sha256:39ebaeea2d0c0dd3686e72c37d9b0dc14b788c65f3aca8d292064ea85870a8b0