Pith. sign in

Paper Citation Record · LEDGER

Patterns and Mechanisms of Contrastive Activation Engineering

As of 19 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2505.03189.

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

pith.paper-citation-record.v1
2505.03189 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:00:08.687935Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-13T19:38:18.674355Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T19:43:11.578855Z

Reference resolution

15 of 15 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved14
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 997387e0-15fc-43cc-80c4-f72d534c6612 · outbound

This paper cites Improving Steering Vectors by Targeting Sparse Autoencoder Features.

Patterns and Mechanisms of Contrastive Activation Engineering Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.637537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.637537Z digest=sha256:5700a07bd5c0ea3f0114218356ac26813ba459e00391198acacb38c9db2e3de7

Observation 9b179569-00f7-4d91-8225-f9c2edbef8f0 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Patterns and Mechanisms of Contrastive Activation Engineering DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.642123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.642123Z digest=sha256:dc19df1e81ae05b708ac00fe715e972b5b69ede686e4f7f24f2c31019b90a5db

Observation cf655b6e-b938-4b78-9e70-46d02e354207 · outbound

This paper cites an unresolved cited work.

Patterns and Mechanisms of Contrastive Activation Engineering Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-16T00:00:08.984759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-16T00:00:08.646101Z digest=sha256:6a15ee0a225a2ea3234b07ac8e88dd883301c5f3518b48d86b249ec8c8d5f712

Observation a966a15a-a961-467a-a241-ba23fc24ae71 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Patterns and Mechanisms of Contrastive Activation Engineering Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.653617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.653617Z digest=sha256:4d7c52b70d676fcc5ecf34f9bd498d02dc74d98af553e68a70b2935f0cd9e781

Observation fb68dae8-d0a3-4756-baf3-704f4a97a111 · outbound

This paper cites Steering Language Model Refusal with Sparse Autoencoders.

Patterns and Mechanisms of Contrastive Activation Engineering Steering Language Model Refusal with Sparse Autoencoders

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.657761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.657761Z digest=sha256:024730a819a7d307a6d86a8465a6878804e5490fd13f0d21ad21090762dff7f3

Observation 85449692-d98b-4319-89f7-f733607e8850 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Patterns and Mechanisms of Contrastive Activation Engineering Steering Llama 2 via Contrastive Activation Addition

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.661340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.661340Z digest=sha256:341761c8aeb01123e24cdc41740c46654801446b620ae81e0cb76345aa170c72

Observation 6b08bfed-7aa8-43f9-a237-80e4e7a0f8a8 · outbound

This paper cites Quantifying Generalization Complexity for Large Language Models.

Patterns and Mechanisms of Contrastive Activation Engineering Quantifying Generalization Complexity for Large Language Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.665600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.665600Z digest=sha256:ee51cc7602e237d09692f247e2da61efb374cbd81b42a46d93ab39dcdada5f8d

Observation 3ed4fff6-f51d-4079-a994-a5c57306a5d0 · outbound

This paper cites Analyzing the Generalization and Reliability of Steering Vectors.

Patterns and Mechanisms of Contrastive Activation Engineering Analyzing the Generalization and Reliability of Steering Vectors

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.670678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.670678Z digest=sha256:460d6c79c1ccc4b028fe4bcfd5a7e488f1fdca5accdf2ad03bd2f6cd54588e3e

Observation 14d9e900-3aca-4d32-a24f-43834c8a4be0 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Patterns and Mechanisms of Contrastive Activation Engineering Gemma 2: Improving Open Language Models at a Practical Size

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.675088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.675088Z digest=sha256:3e9da55b79c25bea29703d7f7d3b7111d2ef698c77124a15d2d6938e63a95667

Observation 135aaedd-947f-40a1-b935-a90d200eb639 · outbound

This paper cites an unresolved cited work.

Patterns and Mechanisms of Contrastive Activation Engineering Unresolved cited work

Reference 13

Resolution
unresolved
raw_fallback, observed 2026-08-16T00:00:08.972029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-16T00:00:08.679686Z digest=sha256:261a5fd86bafaffb5350a44b344f9335f2c07741fda9cdff10fabc97e83ba5c4

Observation ca8a3810-cb36-4ccc-a131-9682b1896ee1 · outbound

This paper cites Fluent dreaming for language models.

Patterns and Mechanisms of Contrastive Activation Engineering Fluent dreaming for language models

Reference 14

Resolution
metadata mismatch
local_arxiv, observed 2026-08-16T00:00:08.754544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-16T00:00:08.683614Z digest=sha256:101243b3072ac8cae42996033aeda93abe52d9bee392387057df6a3784a30991

Observation 2ede3572-477b-4799-a5db-3bce0d7121eb · outbound

This paper cites Steering Language Models With Activation Engineering.

Patterns and Mechanisms of Contrastive Activation Engineering Steering Language Models With Activation Engineering

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.687935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.687935Z digest=sha256:b10e22e139fe6828abb3bd8a4c7cee49ee0711d957f7c71e837dca35c1cc8643

Observation 99daa571-48d6-411e-a589-d9d855167f9c · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Patterns and Mechanisms of Contrastive Activation Engineering The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.649804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.649804Z digest=sha256:80de55fe08a2206403aa1d44766e7109f4fadfdbe795552aa8cebae82b8c7ba7

Observation 910af266-d3ef-4788-97c6-e44e8c4e72fc · outbound

This paper cites LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks.

Patterns and Mechanisms of Contrastive Activation Engineering LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.628192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.628192Z digest=sha256:a22787cc13b7a34c2b327f356770ca6d66aa165cd1ebd95a2cec6a124e988c06

Observation ab260ca0-4f6b-4c00-a14c-f59339a338c6 · outbound

This paper cites Sviatoslav Chalnev, Matthew Siu, and Arthur Conmy.

Patterns and Mechanisms of Contrastive Activation Engineering Sviatoslav Chalnev, Matthew Siu, and Arthur Conmy

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-16T00:00:08.633211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:00:08.633211Z digest=sha256:012f5dd438a373071452d37ce27980d95b26f7d25d35fbd473ed12d036360694

Pith citing papers

Observation 695e2302-695d-470f-841f-a69637ecdf11 · inbound

An Independent Safety Evaluation of Kimi K2.5 cites this paper.

An Independent Safety Evaluation of Kimi K2.5 Patterns and Mechanisms of Contrastive Activation Engineering

Reference 97

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:43:11.580188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-13T19:38:18.674355Z digest=sha256:84ae54ab79bc8dd20f833a449d061aa53407896de0c3df4d3ed55eb30052863e