Paper Citation Record · LEDGER

Minimizing Collateral Damage in Activation Steering

As of 1 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2605.01167.

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

pith.paper-citation-record.v1
2605.01167 v1

Coverage vector

measured 62 of 62 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-09T18:58:30.056670Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-01T06:32:01.292127+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T05:02:03.008494Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

62 of 62 outbound references displayed

verified exact7
verified fuzzy31
unresolved7
parse uncertain1
malformed identifier0
metadata mismatch16

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5c13e7b3-7e12-41e1-8f4e-b2d3002c7d3d · outbound

This paper cites Steering Language Models With Activation Engineering.

Minimizing Collateral Damage in Activation Steering Steering Language Models With Activation Engineering

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:56:49.014489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 884d8a7d-5ef8-4bed-afc3-533a22390db1 · outbound

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

Minimizing Collateral Damage in Activation Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 054ab081-a30f-436e-9bae-51b01aef06f9 · outbound

This paper cites Inference-Time Intervention: Eliciting Truthful Answers from a Language Model.

Minimizing Collateral Damage in Activation Steering Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T09:21:59.414933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation e4df9d5a-4322-4b09-90b7-75db92bc4910 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Minimizing Collateral Damage in Activation Steering Steering Llama 2 via Contrastive Activation Addition

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:37:21.847050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 0d04ea9e-50ad-4dc7-ad3b-9ad82f4f645d · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , articleno =.

Minimizing Collateral Damage in Activation Steering Proceedings of the 41st International Conference on Machine Learning , articleno =

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.385487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c0ebe2af-70a6-47bb-9d50-f71f62cc2aab · outbound

This paper cites T ruth X : Alleviating Hallucinations by Editing Large Language Models in Truthful Space.

Minimizing Collateral Damage in Activation Steering T ruth X : Alleviating Hallucinations by Editing Large Language Models in Truthful Space

Reference 6

Resolution: verified exact; doi, observed 2026-05-09T19:00:07.432274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation ceb93a7e-300c-499c-a55e-fbcc7744eeb2 · outbound

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

Minimizing Collateral Damage in Activation Steering Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T14:28:18.117199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 5c539f9b-3710-428e-8553-639462e0b6d9 · outbound

This paper cites arXiv preprint arXiv:2506.19823 , year =.

Minimizing Collateral Damage in Activation Steering arXiv preprint arXiv:2506.19823 , year =

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:56:48.895291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 247574ce-2d87-40db-8d54-dee4b929fcf5 · outbound

This paper cites The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=.

Minimizing Collateral Damage in Activation Steering The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.374145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 26c9039d-650a-42a2-97aa-ad15ea657e20 · outbound

This paper cites Advances in Neural Information Processing Systems , year=.

Minimizing Collateral Damage in Activation Steering Advances in Neural Information Processing Systems , year=

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.376981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 2d520834-9a43-46af-8419-a9a0f7282023 · outbound

This paper cites Alphasteer: Learn- ing refusal steering with principled null-space constraint.

Minimizing Collateral Damage in Activation Steering Alphasteer: Learn- ing refusal steering with principled null-space constraint

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:56:48.235112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 8dbd61b1-7472-4b4a-8156-167a44dcce4a · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering The Thirteenth International Conference on Learning Representations , year=

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.367439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c45c2441-4fc9-4872-947c-3d0d18e168ec · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering The Thirteenth International Conference on Learning Representations , year=

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.364135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 6d82855d-aaef-4219-ad61-81a89ecb903b · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering The Thirteenth International Conference on Learning Representations , year=

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.370874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 238f889a-8ac8-4604-994e-5f17940a5d04 · outbound

This paper cites 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=.

Minimizing Collateral Damage in Activation Steering 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.379998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation e867ca07-7b58-472f-ba5f-f5d333795470 · outbound

This paper cites Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety.

Minimizing Collateral Damage in Activation Steering Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety

Reference 16

Resolution: verified exact; doi, observed 2026-05-09T19:00:07.434137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation ed8b879d-d6ba-4c57-9bd9-a99799536453 · outbound

This paper cites A da S teer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender.

Minimizing Collateral Damage in Activation Steering A da S teer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

Reference 17

Resolution: verified exact; doi, observed 2026-05-09T19:00:07.421652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 6aaddd3a-8e72-45bb-b763-7303aafa3b3d · outbound

This paper cites Representation Bending for Large Language Model Safety.

Minimizing Collateral Damage in Activation Steering Representation Bending for Large Language Model Safety

Reference 18

Resolution: verified exact; doi, observed 2026-05-09T19:00:07.428120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation f89d1636-b9c9-4ddf-a121-346cc8da07ae · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.382697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation f5f9a9e3-5ebf-472f-ab90-6de7d148f997 · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.388129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation edd1a3f1-4401-43ce-bbd7-ae046a61dd7c · outbound

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

Minimizing Collateral Damage in Activation Steering Gemma 2: Improving Open Language Models at a Practical Size

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:56:48.971892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 518082f0-0edd-4f6d-9e52-8659b399862c · outbound

This paper cites 2023 , eprint=.

Minimizing Collateral Damage in Activation Steering 2023 , eprint=

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.391444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 882b3596-a955-493b-b897-d1199c04f1a5 · outbound

This paper cites Hashimoto , title =.

Minimizing Collateral Damage in Activation Steering Hashimoto , title =

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.358281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation dbba6a29-33be-4441-9eb6-b3e2c79ca7d0 · outbound

This paper cites 2023 , url =.

Minimizing Collateral Damage in Activation Steering 2023 , url =

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.397178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 542617dd-1eff-4d5a-8380-8b8024bf898e · outbound

This paper cites tinyBenchmarks: evaluating LLMs with fewer examples.

Minimizing Collateral Damage in Activation Steering tinyBenchmarks: evaluating LLMs with fewer examples

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:56:48.964867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation a6438887-10fe-4a74-94dd-a43f48b98b4c · outbound

This paper cites Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Minimizing Collateral Damage in Activation Steering Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.324309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c57c65d7-21d7-4882-815b-d7b77fd1bc4e · outbound

This paper cites URL https:// doi.org/10.18653/v1/p19-1472.

Minimizing Collateral Damage in Activation Steering URL https:// doi.org/10.18653/v1/p19-1472

Reference 27

Resolution: metadata mismatch; doi, observed 2026-05-09T19:00:07.424323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T09:08:05.023254+00:00.

Observation 7f43ecb6-db6f-46b2-b7d2-2d6d86b46824 · outbound

This paper cites Communications of the ACM , volume=.

Minimizing Collateral Damage in Activation Steering Communications of the ACM , volume=

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.312478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 198a4601-0cb6-4f6c-917a-15d14b5b6f7e · outbound

This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.

Minimizing Collateral Damage in Activation Steering Proceedings of the International Conference on Learning Representations (ICLR) , year=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.317656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 74c1ee81-060a-48f3-ac4e-45343ff8f71d · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Minimizing Collateral Damage in Activation Steering Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:56:48.145080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 77c1b527-f879-4d7e-9464-9b5a501d50ad · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Minimizing Collateral Damage in Activation Steering Training Verifiers to Solve Math Word Problems

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:56:48.384249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation a77fe527-0768-4651-bef8-b36575335702 · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , articleno =.

Minimizing Collateral Damage in Activation Steering Proceedings of the 41st International Conference on Machine Learning , articleno =

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.293769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 72ee46b2-46f4-43ff-a562-65ca33be804e · outbound

This paper cites BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP , year=.

Minimizing Collateral Damage in Activation Steering BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP , year=

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.320623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 7b7ebb52-cc19-43d1-8d96-29d93d4197a6 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering The Twelfth International Conference on Learning Representations , year=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.400717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 0ddfeca3-e5f9-4979-8803-b82218cd9858 · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , articleno =.

Minimizing Collateral Damage in Activation Steering Proceedings of the 41st International Conference on Machine Learning , articleno =

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.406298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation de41cfff-e8b7-40a5-85df-9c80dd4caf45 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering The Twelfth International Conference on Learning Representations , year=

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.422494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 285bc1ea-3168-4e9b-804b-3301daaff249 · outbound

This paper cites Annual Meeting of the Association for Computational Linguistics , year=.

Minimizing Collateral Damage in Activation Steering Annual Meeting of the Association for Computational Linguistics , year=

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.425419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 1fb53331-2b7a-489c-997b-62585f9c866c · outbound

This paper cites Anisotropy.

Minimizing Collateral Damage in Activation Steering Anisotropy

Reference 38

Resolution: metadata mismatch; doi, observed 2026-05-09T19:00:07.426283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation a8788401-ee0f-47d0-9cc3-346a94818c90 · outbound

This paper cites 2022 , journal=.

Minimizing Collateral Damage in Activation Steering 2022 , journal=

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.419506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 816dac6a-5714-400e-8d71-21d977d36ac4 · outbound

This paper cites Journal of machine learning research , volume=.

Minimizing Collateral Damage in Activation Steering Journal of machine learning research , volume=

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.416099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c91544d7-600e-41ff-b599-48b99eb07a53 · outbound

This paper cites European Conference on Computer Vision , pages=.

Minimizing Collateral Damage in Activation Steering European Conference on Computer Vision , pages=

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.394207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 26c2b38c-80c7-49e5-b87b-f061900cbd96 · outbound

This paper cites Proceedings of the 12th annual conference on Computer graphics and interactive techniques , year=.

Minimizing Collateral Damage in Activation Steering Proceedings of the 12th annual conference on Computer graphics and interactive techniques , year=

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.355375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c79ae231-8af6-4b2a-9454-09f392faf0fd · outbound

This paper cites Sampling Generative Networks.

Minimizing Collateral Damage in Activation Steering Sampling Generative Networks

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:56:48.646305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 88d85de6-43b9-4bd5-bf28-d9e8516917f8 · outbound

This paper cites Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLM s with Direction-Magnitude Perspective.

Minimizing Collateral Damage in Activation Steering Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLM s with Direction-Magnitude Perspective

Reference 44

Resolution: verified exact; doi, observed 2026-05-09T19:00:07.429932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation ae6cbe29-8ad2-4803-aea9-21ee69dcff84 · outbound

This paper cites 2004 , publisher=.

Minimizing Collateral Damage in Activation Steering 2004 , publisher=

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.403731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 79cb4bd9-0097-46de-bf2c-cffde5c78f79 · outbound

This paper cites 2013 , publisher=.

Minimizing Collateral Damage in Activation Steering 2013 , publisher=

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.345226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 7f5b5526-9e04-4ee9-ac5e-635ad0984009 · outbound

This paper cites CS294A Lecture notes , volume=.

Minimizing Collateral Damage in Activation Steering CS294A Lecture notes , volume=

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.342337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 8679e2de-3f80-4f7f-bdbe-73942b056e2e · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering The Thirteenth International Conference on Learning Representations , year=

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.412345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation ebbbd095-b320-41c2-a3a2-2ecfaa9a0d88 · outbound

This paper cites Connor Kissane, Robert Krzyzanowski, Arthur Conmy, and Neel Nanda.

Minimizing Collateral Damage in Activation Steering Connor Kissane, Robert Krzyzanowski, Arthur Conmy, and Neel Nanda

Reference 49

Resolution: metadata mismatch; doi, observed 2026-05-09T19:00:07.444573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation dc9a264b-3083-48dc-95bd-7414c9151c9c · outbound

This paper cites The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models.

Minimizing Collateral Damage in Activation Steering The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.348552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 61387b6d-bfb0-4d7b-bf6e-39a7bf958bce · outbound

This paper cites Instruction Tuning for Large Language Models: A Survey.ACM Computing Surveys, page 3777411, November 2025.

Minimizing Collateral Damage in Activation Steering Instruction Tuning for Large Language Models: A Survey.ACM Computing Surveys, page 3777411, November 2025

Reference 51

Resolution: verified exact; doi, observed 2026-05-09T19:00:07.439403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation e0cd9ce3-2efc-4ef6-9c6f-b57a68b52bc5 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Minimizing Collateral Damage in Activation Steering Fine-Tuning Language Models from Human Preferences

Reference 52

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:56:48.327077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 2462c695-c7df-404c-b651-d0fd347765a6 · outbound

This paper cites International Conference on Learning Representations , year=.

Minimizing Collateral Damage in Activation Steering International Conference on Learning Representations , year=

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.352113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 45bd83a8-86e7-465b-a36b-21603537dcc8 · outbound

This paper cites Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models.

Minimizing Collateral Damage in Activation Steering Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models

Reference 54

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:56:48.504431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c2b1516d-4598-4bee-8663-46ea0770c308 · outbound

This paper cites Langley , title =.

Minimizing Collateral Damage in Activation Steering Langley , title =

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.361250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 2cb9eddb-159e-47ac-beb9-ee9216873c94 · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.335857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation e86cfed8-2233-4aa6-ad92-9c3b407266b5 · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 57

Resolution: parse uncertain; raw_fallback, observed 2026-05-25T22:21:18.339563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation e477167c-4581-4477-892e-1b2c916495ee · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.332502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation f2a3f64b-31c6-4b44-9e8c-776106af5791 · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.287422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation b0d4a169-c861-4c0f-add4-b3634d69d57c · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.290518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 586dbc73-ff79-4e22-b229-2f9d36b85bf5 · outbound

This paper cites Newell and P.

Minimizing Collateral Damage in Activation Steering Newell and P

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:21:18.327041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 5cd337ed-0fd0-4f1d-8bdf-f6b834e8a5ec · outbound

This paper cites an unresolved cited work.

Minimizing Collateral Damage in Activation Steering Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:21:18.329687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Pith citing papers

Observation b4838b5f-98e9-4575-b5d9-f1b9b851d034 · inbound

Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering cites this paper.

Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering Minimizing Collateral Damage in Activation Steering

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T05:02:03.008494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.