Paper Citation Record · LEDGER

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents

As of 21 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2607.07474.

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

pith.paper-citation-record.v1
2607.07474 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-09T09:58:33.074127Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

15 of 15 outbound references displayed

verified exact3
verified fuzzy12
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f329a4e4-e2ab-4405-a5ab-19bc81ea1324 · outbound

This paper cites AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.830115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5e77a14b-ae83-4d8e-b068-d15d8b446ab0 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Ignore Previous Prompt: Attack Techniques For Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:06:09.426173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6a4796d0-893d-43c6-b4cd-ee67e3a4962f · outbound

This paper cites InjecAgent: Benchmark- ing indirect prompt injections in tool-integrated large language model agents,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents InjecAgent: Benchmark- ing indirect prompt injections in tool-integrated large language model agents,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.835226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 629a4ee0-7691-40b8-aae4-babea257c536 · outbound

This paper cites ADVERSA: Mea- suring multi-turn guardrail degradation and judge reliability in large language models,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents ADVERSA: Mea- suring multi-turn guardrail degradation and judge reliability in large language models,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.832758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 12f48316-5f7c-4eff-b2e3-80f028c3c7f4 · outbound

This paper cites JailbreakBench: An open robustness benchmark for jailbreaking large language models,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents JailbreakBench: An open robustness benchmark for jailbreaking large language models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.841993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f26b4ddd-02a2-4902-8427-e8f34dc086a2 · outbound

This paper cites HarmBench: A standardized evaluation framework for automated red teaming and robust refusal,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents HarmBench: A standardized evaluation framework for automated red teaming and robust refusal,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.844835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 136221e8-08cf-4653-beec-facdc9664000 · outbound

This paper cites Judging LLM-as-a-judge with MT-Bench and chatbot arena,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Judging LLM-as-a-judge with MT-Bench and chatbot arena,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.830468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dfdb03d1-e563-472f-ad8e-9a70e235cd4e · outbound

This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:06:09.420192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 358c93f0-d47b-451d-a369-bf82be8f779e · outbound

This paper cites AgentHarm: A benchmark for measuring harmfulness of LLM agents,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents AgentHarm: A benchmark for measuring harmfulness of LLM agents,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.836959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f401d6e1-d70b-4686-ace5-70b10ea3a7b9 · outbound

This paper cites Taxonomy of risks posed by language models,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Taxonomy of risks posed by language models,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.832590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f76259b2-1058-4ee6-9a6f-93fa6e66306a · outbound

This paper cites Identifying the risks of LM agents with an LM-emulated sandbox,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Identifying the risks of LM agents with an LM-emulated sandbox,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.847250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6c5ff330-47e1-4e86-83ba-2d886cc74d0d · outbound

This paper cites R-Judge: Benchmarking safety risk awareness for LLM agents,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents R-Judge: Benchmarking safety risk awareness for LLM agents,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.838988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation be88d3f4-7474-477d-8862-968b54c65ca5 · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:06:09.423395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7ca6f8d6-ce35-4843-bc70-f732e0778ede · outbound

This paper cites Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.837386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0b491060-caf6-4740-a192-978b62316712 · outbound

This paper cites Computing Krippendorff’s alpha-reliability,.

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Computing Krippendorff’s alpha-reliability,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T10:06:09.850156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.