Paper Citation Record · LEDGER

Inverted Detection and Control in Steering Vectors

As of 17 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2608.02957.

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

pith.paper-citation-record.v1
2608.02957 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:00:38.197250Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

45 of 45 outbound references displayed

verified exact2
verified fuzzy9
unresolved33
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 03efd33d-4295-4394-af5f-386a78c52937 · outbound

This paper cites Layer Normalization.

Inverted Detection and Control in Steering Vectors Layer Normalization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.049206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27c1b384-693c-49c0-8971-2d71431226b2 · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022.

Inverted Detection and Control in Steering Vectors Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.053266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698456c0-feae-49db-98f8-acda51dd51eb · outbound

This paper cites Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering.

Inverted Detection and Control in Steering Vectors Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.056650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b94d2b41-60e5-42a2-a7e1-dbca2818c079 · outbound

This paper cites Understanding (Un)Reliability of Steering Vectors in Language Models.

Inverted Detection and Control in Steering Vectors Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.060792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc6e9a3-5459-46bc-a72a-7d2241c1e988 · outbound

This paper cites Personalized steering of large language models: Versatile steering vectors through bi-directional preference optimization.

Inverted Detection and Control in Steering Vectors Personalized steering of large language models: Versatile steering vectors through bi-directional preference optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.064820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec63d09-bdf0-48c2-9a07-fd78157645d0 · outbound

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

Inverted Detection and Control in Steering Vectors Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.068608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 925ea5fd-ae03-4360-a37c-931787d32b88 · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread, 1(1):12, 2021.

Inverted Detection and Control in Steering Vectors A mathematical framework for transformer circuits.Transformer Circuits Thread, 1(1):12, 2021

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.072797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047f348a-b4eb-44f4-b586-0b6996e1504e · outbound

This paper cites Dermatologist-level classification of skin cancer with deep neural networks.

Inverted Detection and Control in Steering Vectors Dermatologist-level classification of skin cancer with deep neural networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.076041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3406ac3-73c6-4f7e-b339-f5f27a7b3fd3 · outbound

This paper cites New, improved multiple-choice truth- fulqa, 2025.

Inverted Detection and Control in Steering Vectors New, improved multiple-choice truth- fulqa, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.079381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b63822a-8d24-4e4a-a389-de128a3c4209 · outbound

This paper cites Who’s asking? user personas and the mechanics of latent misalignment.Advances in Neural Information Processing Systems, 37:125967–126003, 2024.

Inverted Detection and Control in Steering Vectors Who’s asking? user personas and the mechanics of latent misalignment.Advances in Neural Information Processing Systems, 37:125967–126003, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.082675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5fa0e0a-d053-4413-b708-a1fe451a5732 · outbound

This paper cites Gmail is entering the gemini era, 2026.

Inverted Detection and Control in Steering Vectors Gmail is entering the gemini era, 2026

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.786843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 40ab140f-511b-401b-bb56-35a0cc0e1ec3 · outbound

This paper cites Empirical asset pricing via machine learning.The Review of Financial Studies, 33(5):2223–2273, 2020.

Inverted Detection and Control in Steering Vectors Empirical asset pricing via machine learning.The Review of Financial Studies, 33(5):2223–2273, 2020

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.089323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d3bcd21-db47-4153-8377-83eb2d63398d · outbound

This paper cites Deep residual learning for image recognition.

Inverted Detection and Control in Steering Vectors Deep residual learning for image recognition

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.092407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9767afbd-f48d-44ae-8a0e-a70b28e0e6ae · outbound

This paper cites Probability inequalities for sums of bounded random variables.Journal of the American statistical association, 58(301):13–30, 1963.

Inverted Detection and Control in Steering Vectors Probability inequalities for sums of bounded random variables.Journal of the American statistical association, 58(301):13–30, 1963

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.095390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 734c4f8c-09e4-4210-88ea-1b5e037bbdd1 · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1 (2):3, 2022.

Inverted Detection and Control in Steering Vectors Lora: Low-rank adaptation of large language models.ICLR, 1 (2):3, 2022

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.098770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7baba128-ee49-49a0-9f9b-265a93067a6c · outbound

This paper cites Steering Protein Language Models.

Inverted Detection and Control in Steering Vectors Steering Protein Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.101968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986b377c-b092-493b-ad1a-63724eee83d9 · outbound

This paper cites A unified understanding and evaluation of steering methods.arXiv preprint arXiv:2502.02716, 2025.

Inverted Detection and Control in Steering Vectors A unified understanding and evaluation of steering methods.arXiv preprint arXiv:2502.02716, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.105352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68ea4aa-7c14-412c-8a1d-25219b0269a4 · outbound

This paper cites Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models.

Inverted Detection and Control in Steering Vectors Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:00:38.517450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 68ebaed7-38f3-459b-9e6b-0c4fed92d22f · outbound

This paper cites Gemma 3 Technical Report.

Inverted Detection and Control in Steering Vectors Gemma 3 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.112237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 505bc0b5-d744-47eb-80f7-320f6c866c02 · outbound

This paper cites Steering vector fields for context-aware inference- time control in large language models.arXiv preprint arXiv:2602.01654, 2026.

Inverted Detection and Control in Steering Vectors Steering vector fields for context-aware inference- time control in large language models.arXiv preprint arXiv:2602.01654, 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.115841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fdb409f-28f1-4a94-8d7e-a4348069a0aa · outbound

This paper cites Inference- time intervention: Eliciting truthful answers from a language model.Advances in Neural Information Processing Systems, 36:41451–41530, 2023.

Inverted Detection and Control in Steering Vectors Inference- time intervention: Eliciting truthful answers from a language model.Advances in Neural Information Processing Systems, 36:41451–41530, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.118918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b12b0a06-f26e-4199-a9ef-4405bf66b4dc · outbound

This paper cites Truthfulqa: Measuring how models mimic human falsehoods.

Inverted Detection and Control in Steering Vectors Truthfulqa: Measuring how models mimic human falsehoods

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.122180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb68cb08-d207-4bfd-8545-fc30361d4d05 · outbound

This paper cites The assis- tant axis: Situating and stabilizing the default persona of language models.arXiv preprint arXiv:2601.10387, 2026.

Inverted Detection and Control in Steering Vectors The assis- tant axis: Situating and stabilizing the default persona of language models.arXiv preprint arXiv:2601.10387, 2026

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.125446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1df0ae4d-2ced-4fb9-8f80-5562c4f802d4 · outbound

This paper cites Levi strauss & co.

Inverted Detection and Control in Steering Vectors Levi strauss & co

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.738007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c35e9b79-f39a-4f53-b87a-0b9541cd3b75 · outbound

This paper cites Nfl and microsoft expand partnership to bring copilot to the sidelines and beyond.

Inverted Detection and Control in Steering Vectors Nfl and microsoft expand partnership to bring copilot to the sidelines and beyond

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.726738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1c9ae8c8-079d-40a2-b7b9-538db99acca2 · outbound

This paper cites Olmo 3.

Inverted Detection and Control in Steering Vectors Olmo 3

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.134962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4614946-b717-4deb-a11d-31ca103bb28e · outbound

This paper cites The linear representation hypothesis and the geometry of large language models.

Inverted Detection and Control in Steering Vectors The linear representation hypothesis and the geometry of large language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.715355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7cc8f53a-8099-4ca2-b33a-f7b175cd7871 · outbound

This paper cites Discovering language model behaviors with model-written evaluations.

Inverted Detection and Control in Steering Vectors Discovering language model behaviors with model-written evaluations

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.141849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340ffd08-67c7-48db-92ee-b46fe78a03b8 · outbound

This paper cites Spectral editing of activations for large language model alignment.Advances in Neural Information Processing Systems, 37:56958–56987, 2024.

Inverted Detection and Control in Steering Vectors Spectral editing of activations for large language model alignment.Advances in Neural Information Processing Systems, 37:56958–56987, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.144818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a78b43f7-0118-48b7-aac1-07b3af5345ba · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Inverted Detection and Control in Steering Vectors Steering llama 2 via contrastive activation addition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.148005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e7139ed-ebde-4e94-a494-7cc27cc3acf8 · outbound

This paper cites Controlling language and diffusion models by transporting activations.

Inverted Detection and Control in Steering Vectors Controlling language and diffusion models by transporting activations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.151173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c84a72-c5df-461c-b4d9-8f8755b3a8fb · outbound

This paper cites Activation steering via generative causal mediation.arXiv preprint arXiv:2602.16080, 2026.

Inverted Detection and Control in Steering Vectors Activation steering via generative causal mediation.arXiv preprint arXiv:2602.16080, 2026

Reference 32

Resolution: verified exact; raw_fallback, observed 2026-08-15T15:00:38.351690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8bfafef2-4b81-4a6e-9cf6-dcf020f059e8 · outbound

This paper cites Open problems in mechanistic interpretability.Transactions on Machine Learning Research, 2025.

Inverted Detection and Control in Steering Vectors Open problems in mechanistic interpretability.Transactions on Machine Learning Research, 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.685251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 516be95c-2e5d-44b2-a32c-af334fbe2447 · outbound

This paper cites RepIt: Steering Language Models with Concept-Specific Refusal Vectors.

Inverted Detection and Control in Steering Vectors RepIt: Steering Language Models with Concept-Specific Refusal Vectors

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.160878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48907f14-0f4e-4a91-9fff-f79a9e131e3e · outbound

This paper cites Analysing the generalisation and reliability of steering vectors.

Inverted Detection and Control in Steering Vectors Analysing the generalisation and reliability of steering vectors

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.673299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1fd9ed98-62e0-4262-9598-1938cc00a5b1 · outbound

This paper cites Function vectors in large language models.

Inverted Detection and Control in Steering Vectors Function vectors in large language models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.661310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 999368fd-c6e6-40c9-aa77-74d973b3418a · outbound

This paper cites DISCO: Disentangled com- munication steering for large language models.

Inverted Detection and Control in Steering Vectors DISCO: Disentangled com- munication steering for large language models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.171302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9210e88-1a77-4299-8acd-f6327c36541e · outbound

This paper cites CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering.

Inverted Detection and Control in Steering Vectors CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.174652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 122775ca-b9a3-48e3-9ea4-4bbc70d53e3c · outbound

This paper cites Relational Composition in Neural Networks: A Survey and Call to Action.

Inverted Detection and Control in Steering Vectors Relational Composition in Neural Networks: A Survey and Call to Action

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.178023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f14348b9-122c-4277-a410-ee122d5702fe · outbound

This paper cites Reft: Representation finetuning for language models.Advances in Neural Information Processing Systems, 37:63908–63962, 2024.

Inverted Detection and Control in Steering Vectors Reft: Representation finetuning for language models.Advances in Neural Information Processing Systems, 37:63908–63962, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.181449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ee8c3dc-41ae-45d0-9aa5-9d79a82c5a87 · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

Inverted Detection and Control in Steering Vectors AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.184550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb280638-4315-4f4e-b834-073c8051f6a7 · outbound

This paper cites Qwen2.5 Technical Report.

Inverted Detection and Control in Steering Vectors Qwen2.5 Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.187905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b31b9f2-17ef-4257-9be7-603206419bed · outbound

This paper cites Lofit: Localized fine-tuning on LLM representations.

Inverted Detection and Control in Steering Vectors Lofit: Localized fine-tuning on LLM representations

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.637882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 03f22a81-86ba-41d2-9015-e2f4391b53bd · outbound

This paper cites Deal: Disentangling transformer head activations for llm steering.

Inverted Detection and Control in Steering Vectors Deal: Disentangling transformer head activations for llm steering

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:00:38.626533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9e7702b0-c52a-4027-b3ac-00cd3f9ae2ce · outbound

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

Inverted Detection and Control in Steering Vectors Representation Engineering: A Top-Down Approach to AI Transparency

Reference 45

Resolution: malformed identifier; no resolver link, observed 2026-08-15T15:00:38.197250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.