Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-01T00:59:08.647382Z
Paper Citation Record · LEDGER
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications
As of 10 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2607.25987.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
16 of 16 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved15
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation f5032b95-a6bf-4513-b8b8-9130276caed2 · outbound
This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.360105Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af6a9c7b-1a57-4199-9968-4ffc3d18cb43 · outbound
This paper cites Identifying the Risks of LM Agents with an LM-Emulated Sandbox.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.737179Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e501860c-869b-4a37-af8f-7800225657f8 · outbound
This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.824949Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 43fbe682-5dd9-4eea-9218-0ed9431fa3b7 · outbound
This paper cites Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.912538Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 862c8ff8-9db9-4972-99d6-16918a393b08 · outbound
This paper cites xAI Inference REST API Overview.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications xAI Inference REST API Overview
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.014238Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1190ddb-bff2-498e-a945-c7cfd206eb0a · outbound
This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.113657Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d2ac8360-d29e-428f-bcd8-2bf4a99ab2e3 · outbound
This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.246438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 192de2ae-f253-4f5a-934a-b6eb726b09f8 · outbound
This paper cites Iheval: Evaluating language models on following the instruction hierarchy.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Iheval: Evaluating language models on following the instruction hierarchy
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.287438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a3197632-d4fb-4b55-97e1-0e4b6dc65067 · outbound
This paper cites Instruction-Following Evaluation for Large Language Models.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Instruction-Following Evaluation for Large Language Models
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.374290Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8ed0d429-a201-41f9-9f3c-46d76671d181 · outbound
This paper cites Y denotes primary coverage, P denotes partial or adjacent coverage, and – denotes not a primary focus.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Y denotes primary coverage, P denotes partial or adjacent coverage, and – denotes not a primary focus
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.488331Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ddba0c7b-0bf6-4259-994b-7297486fefdb · outbound
This paper cites 11 Table 7: Model providers and exact LiteLLM identifiers for all 37 model variants.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications 11 Table 7: Model providers and exact LiteLLM identifiers for all 37 model variants
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:08.573160Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ecdbc884-167c-4563-86d6-355642116961 · outbound
This paper cites an unresolved cited work.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Unresolved cited work
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.575558Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 612054c2-2e3e-4896-a039-cf4e4abbce49 · outbound
This paper cites LiteLLM: Open-source library and ai gateway for calling llm providers.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications LiteLLM: Open-source library and ai gateway for calling llm providers
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.438286Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4f575bf0-1f27-49fd-a761-31bfc0883ea9 · outbound
This paper cites Infobench: Evaluating instruction following ability in large language models.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Infobench: Evaluating instruction following ability in large language models
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.682201Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0cb2c6de-60f5-4edf-be89-7bccc48680a0 · outbound
This paper cites Ih-challenge: A training dataset to improve instruction hierarchy on frontier llms.arXiv preprint arXiv:2603.10521,.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications Ih-challenge: A training dataset to improve instruction hierarchy on frontier llms.arXiv preprint arXiv:2603.10521,
Reference 2026
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:59:07.505407Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation beab5425-507b-4bef-b8f7-e1ce267c1226 · outbound
This paper cites no action required.
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications no action required
Reference 8192
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-01T00:59:08.647382Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.