Paper Citation Record · LEDGER

Steering Conceptual Bias via Transformer Latent-Subspace Activation

As of 22 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2506.18887.

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

pith.paper-citation-record.v1
2506.18887 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:44:55.515108Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-16T12:39:57.398423Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T12:40:54.668613Z

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy4
unresolved18
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aec80db6-5743-43c8-9b08-120f0453c69e · outbound

This paper cites Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.408876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7851e1a-ffb4-4d3e-9b37-dada61562c6f · outbound

This paper cites Juhee Kim, Woohyuk Choi, and Byoungyoung Lee.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Juhee Kim, Woohyuk Choi, and Byoungyoung Lee

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.415219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d135000-4b79-4c9e-8c85-107d2324242e · outbound

This paper cites Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.421104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c63bfe-0596-4ab6-bba2-962ba17708a8 · outbound

This paper cites AtP*: An efficient and scalable method for localizing LLM behaviour to components.

Steering Conceptual Bias via Transformer Latent-Subspace Activation AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.426570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 107d23ea-3dec-4bc8-a1e4-425433cc1c93 · outbound

This paper cites AI Agents: Evolution, Architecture, and Real-World Applications.

Steering Conceptual Bias via Transformer Latent-Subspace Activation AI Agents: Evolution, Architecture, and Real-World Applications

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.433224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dee178b-85ac-478e-955b-838cd8d868c8 · outbound

This paper cites The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery.

Steering Conceptual Bias via Transformer Latent-Subspace Activation The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.440084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa897a9f-2468-4c9e-94ac-e1f27dae4265 · outbound

This paper cites In-context Learning and Induction Heads.

Steering Conceptual Bias via Transformer Latent-Subspace Activation In-context Learning and Induction Heads

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.451788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc564ae-71fd-44ff-b9d5-66472d7f3319 · outbound

This paper cites Steer LLM Latents for Hallucination Detection.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Steer LLM Latents for Hallucination Detection

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.458608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db09ebd7-c18a-44b4-a93c-10e58bb7ee78 · outbound

This paper cites Qwen2.5 Technical Report.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Qwen2.5 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.465237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87407910-964c-4ff2-b9d2-c5f78fe65594 · outbound

This paper cites doi: https://doi.org/10.1016/j.egyai.

Steering Conceptual Bias via Transformer Latent-Subspace Activation doi: https://doi.org/10.1016/j.egyai

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-08-15T18:44:55.471291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62608aba-38b9-4a91-be00-b35d6b6b2bf4 · outbound

This paper cites an unresolved cited work.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:44:56.211560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 81a4bd8c-9d1a-4368-aac1-e19dad5e1251 · outbound

This paper cites SciCode: A Research Coding Benchmark Curated by Scientists.

Steering Conceptual Bias via Transformer Latent-Subspace Activation SciCode: A Research Coding Benchmark Curated by Scientists

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.482840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf76df3-03af-46ea-86c3-64cc89297d78 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.494356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65f24b10-56a3-444e-b25d-8b3069cd7fec · outbound

This paper cites A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024a.

Steering Conceptual Bias via Transformer Latent-Subspace Activation A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024a

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:44:56.176337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8849860e-a0d5-4508-8efc-d0f570c81cb8 · outbound

This paper cites ISBN 9798400712746.

Steering Conceptual Bias via Transformer Latent-Subspace Activation ISBN 9798400712746

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.504427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea66b4ae-f3d6-4097-ab73-6855d4c40dd5 · outbound

This paper cites Wei Jie Yeo, Rui Mao, Moloud Abdar, Erik Cambria, and Ranjan Satapathy.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Wei Jie Yeo, Rui Mao, Moloud Abdar, Erik Cambria, and Ranjan Satapathy

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.509432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a817efc7-3f1b-4e4f-bc6d-5aab5a73d4e2 · outbound

This paper cites Interpreting the Repeated Token Phenomenon in Large Language Models.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Interpreting the Repeated Token Phenomenon in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.515108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2ab8d3-467b-407f-9c8b-554b43564c89 · outbound

This paper cites ISBN 9780898716245.

Steering Conceptual Bias via Transformer Latent-Subspace Activation ISBN 9780898716245

Reference 2007

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:44:56.246984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e5150d87-9cd6-4f3b-919d-e6ff7541ea2a · outbound

This paper cites Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:44:56.194675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 552b65a4-cad3-41c8-b57a-73cc6bd9f3e8 · outbound

This paper cites Plug and Play Language Models: A Simple Approach to Controlled Text Generation.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.385114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97f920df-0002-4c34-9034-79877c4556d7 · outbound

This paper cites Shanghua Gao, Ada Fang, Yepeng Huang, Valentina Giunchiglia, Ayush Noori, Jonathan Richard Schwarz, Yasha Ektefaie, Jovana Kondic, and Marinka Zitnik.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Shanghua Gao, Ada Fang, Yepeng Huang, Valentina Giunchiglia, Ayush Noori, Jonathan Richard Schwarz, Yasha Ektefaie, Jovana Kondic, and Marinka Zitnik

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:44:56.229372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6045d1cf-13c2-4fb2-9ceb-82ba3af6dd60 · outbound

This paper cites From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs.

Steering Conceptual Bias via Transformer Latent-Subspace Activation From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs

Reference 2023

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T18:44:55.943946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b5731125-5eaf-40d3-b944-040e61a8a79b · outbound

This paper cites The Llama 3 Herd of Models.

Steering Conceptual Bias via Transformer Latent-Subspace Activation The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.402743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e387ea4-eb72-4cc5-9931-40d0cff0ecb5 · outbound

This paper cites Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head.

Steering Conceptual Bias via Transformer Latent-Subspace Activation Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models with the LM-Head

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T18:44:55.391452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e4c32925-3884-4045-8ef4-cbbbea534dcf · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Steering Conceptual Bias via Transformer Latent-Subspace Activation

Reference 269

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.670569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.