Paper Citation Record · LEDGER

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

As of 7 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2602.06911.

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

pith.paper-citation-record.v1
2602.06911 v2

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:46:14.886511Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

24 of 24 outbound references displayed

verified exact1
verified fuzzy0
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6b3c9b1a-0ab6-4c15-a931-653918c625e9 · outbound

This paper cites (2024b) and He et al.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering (2024b) and He et al

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.881989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fca2ddee-d6b6-4785-bc9d-149889d497c6 · outbound

This paper cites an unresolved cited work.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.886511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cff9a125-00ba-468c-82d0-26bad94a0713 · outbound

This paper cites Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.790420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4568aedc-7d58-427e-81da-1c1653284209 · outbound

This paper cites Luxi He, Mengzhou Xia, and Peter Henderson.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Luxi He, Mengzhou Xia, and Peter Henderson

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.804852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2abbcde9-9b3d-4e54-821c-3b459b676b2f · outbound

This paper cites URL https://openreview.net/forum?id= dp24p8i8Cg.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering URL https://openreview.net/forum?id= dp24p8i8Cg

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.809451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608c4094-fe7d-42db-91c4-eba22db57296 · outbound

This paper cites ISBN 9798400702310.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering ISBN 9798400702310

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.813546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f32768-a236-43d8-87c2-5e2116809be0 · outbound

This paper cites Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.818615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b2ab5f4-48a5-42c5-940d-b15044b12f3a · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.823403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb19529a-d2d8-4a57-9bf5-95359a4f35ba · outbound

This paper cites Kyle O’Brien, Stephen Casper, Quentin Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, and Stella Biderman.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Kyle O’Brien, Stephen Casper, Quentin Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, and Stella Biderman

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.828547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf606279-0b01-4581-b299-aef4377bcd57 · outbound

This paper cites an unresolved cited work.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.833451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608a7c66-ce8d-4b04-83d4-bfae2e8e242b · outbound

This paper cites GPT-4 Technical Report.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering GPT-4 Technical Report

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.838787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7013b613-6c98-4212-b40b-295c0e22d8b8 · outbound

This paper cites ISBN 979-8-89176-195-7.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering ISBN 979-8-89176-195-7

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.843583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8193f5d1-1bd8-44cb-a112-509f52876962 · outbound

This paper cites Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, and Sam Toyer.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, and Sam Toyer

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.848303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fdc5205-36e5-4029-b521-a08d041a72e9 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.852644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635d0d1f-45f5-4ec1-8ad7-6709e7139deb · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Jailbroken: How Does LLM Safety Training Fail?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.857511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f31a21da-f524-4d98-b1b9-ad927f168a17 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Instruction-Following Evaluation for Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.862258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b65f4ac7-03a7-42dc-ae07-5bddd6793393 · outbound

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

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.866706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15d922c-090f-4bc9-b23a-810b20f1fdfb · outbound

This paper cites In contrast, MATH is only loosely aligned, reflecting its narrower domain and strict exact-match scoring.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering In contrast, MATH is only loosely aligned, reflecting its narrower domain and strict exact-match scoring

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.871822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b62e94-65d5-4550-83c5-7ea3324b2509 · outbound

This paper cites Danny Halawi, Alexander Wei, Eric Wallace, Tony Wang, Nika Haghtalab, and Jacob Steinhardt.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Danny Halawi, Alexander Wei, Eric Wallace, Tony Wang, Nika Haghtalab, and Jacob Steinhardt

Reference 23

Resolution: verified exact; doi, observed 2026-08-03T03:49:47.372290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e417595e-ea0f-4b95-bf7e-fc2ac3fc5515 · outbound

This paper cites Program Synthesis with Large Language Models.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Program Synthesis with Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.775654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f71dea-bc28-4e6c-b53a-e7ab0e8ac61e · outbound

This paper cites The current year is 2025.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering The current year is 2025

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.877674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c7b69ad-4a16-441c-9139-d0d94dad80b3 · outbound

This paper cites Eternal Sunshine of the Spotless Net: Selec- tive Forgetting in Deep Networks.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Eternal Sunshine of the Spotless Net: Selec- tive Forgetting in Deep Networks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.796043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79061286-4169-4c8f-8f42-9b3413502b80 · outbound

This paper cites URL https://openreview.net/forum?id=urjPCYZt0I.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering URL https://openreview.net/forum?id=urjPCYZt0I

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.785957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e96d75aa-c237-4a1d-a88c-2607b78ab112 · outbound

This paper cites Defending Against Unforeseen Failure Modes with Latent Adversarial Training.

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T03:46:14.781234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.