Paper Citation Record · LEDGER

GPT-Red: Automated Red Teaming via Self-Play at Scale

As of 9 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2607.26115.

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

pith.paper-citation-record.v1
2607.26115 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T01:12:44.201592Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7be87c14-6d5f-4a38-83dc-6b1456f5942a · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

GPT-Red: Automated Red Teaming via Self-Play at Scale AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.130108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e14ae957-196f-4a65-a724-239d6e7160d5 · outbound

This paper cites How vulnerable are ai agents to indirect prompt injections? insights from a large‐ scalepubliccompetition.

GPT-Red: Automated Red Teaming via Self-Play at Scale How vulnerable are ai agents to indirect prompt injections? insights from a large‐ scalepubliccompetition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.135153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64677a4b-47eb-40e2-af4b-f333ce154e4c · outbound

This paper cites MART: Improving LLM Safety with Multi-round Automatic Red-Teaming.

GPT-Red: Automated Red Teaming via Self-Play at Scale MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.140186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad47015-6eeb-423d-8168-b57de8d569cb · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

GPT-Red: Automated Red Teaming via Self-Play at Scale Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.145869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04b3dc29-8c72-48d4-bcbf-e2af7d5700b8 · outbound

This paper cites Red Teaming Language Models with Language Models.

GPT-Red: Automated Red Teaming via Self-Play at Scale Red Teaming Language Models with Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.151768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd147938-f0fd-44a5-bc2b-366b870efa8e · outbound

This paper cites Toyer, S., Watkins, O., Mendes, E.

GPT-Red: Automated Red Teaming via Self-Play at Scale Toyer, S., Watkins, O., Mendes, E

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.164253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c76f5e9b-e5d3-4311-b3ff-1e806e38fac5 · outbound

This paper cites AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents.

GPT-Red: Automated Red Teaming via Self-Play at Scale AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.169745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 717e47b6-1b6c-41c6-9307-4c7c5dc2ca33 · outbound

This paper cites Xu, H., Zhang, W., Wang, Z., Xiao, F., Zheng, R., Feng, Y., Ba, Z., and Ren, K.

GPT-Red: Automated Red Teaming via Self-Play at Scale Xu, H., Zhang, W., Wang, Z., Xiao, F., Zheng, R., Feng, Y., Ba, Z., and Ren, K

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.174390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3b09427-a1e8-4a06-a09e-bb0a28d19412 · outbound

This paper cites From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training.

GPT-Red: Automated Red Teaming via Self-Play at Scale From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.184834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c4aff08-d08a-456a-9bd9-6ea58d236fa6 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

GPT-Red: Automated Red Teaming via Self-Play at Scale InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.189784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03156622-021f-43a8-884d-63311c262b19 · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

GPT-Red: Automated Red Teaming via Self-Play at Scale Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.195947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c442ccb6-1671-4e00-a6cb-4a169654a8a0 · outbound

This paper cites Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition.

GPT-Red: Automated Red Teaming via Self-Play at Scale Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.201592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0e98fb-81ec-46f8-8f73-c93b7bb478cb · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

GPT-Red: Automated Red Teaming via Self-Play at Scale Constitutional AI: Harmlessness from AI Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.113665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed6572bb-4fb9-4054-b5d4-bdafaec6e790 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

GPT-Red: Automated Red Teaming via Self-Play at Scale Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.124317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9a38d2f-ccfa-47e0-bf9f-04bd2014c4c3 · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

GPT-Red: Automated Red Teaming via Self-Play at Scale AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.107279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8a800fe-adaf-4bc1-b6ff-5bf651c93279 · outbound

This paper cites Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning.

GPT-Red: Automated Red Teaming via Self-Play at Scale Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.118461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c63fa4-9d67-41ee-948b-c36bd79adb0b · outbound

This paper cites Lessons from Defending Gemini Against Indirect Prompt Injections.

GPT-Red: Automated Red Teaming via Self-Play at Scale Lessons from Defending Gemini Against Indirect Prompt Injections

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.157635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1582961c-4a0f-43f7-ac87-96b5e90e24af · outbound

This paper cites Prompt Injection as Role Confusion.

GPT-Red: Automated Red Teaming via Self-Play at Scale Prompt Injection as Role Confusion

Reference 6667

Resolution: unresolved; no resolver link, observed 2026-08-01T01:12:44.179664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.