Paper Citation Record · LEDGER

Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

As of 3 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 39 inbound Pith citation observations for arXiv:2408.08926.

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

pith.paper-citation-record.v1
2408.08926 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 39 of 39 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T00:49:47.662275Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T18:37:31.168670Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 0feb9130-5989-413f-818a-86b3d31b83ba · inbound

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

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T01:35:51.135418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 936f24ff-bbee-4b68-afa7-b98308ff62ee · inbound

Frontier Models are Capable of In-context Scheming cites this paper.

Frontier Models are Capable of In-context Scheming Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T14:22:01.635191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation be75ed09-53c6-4815-a5d7-86f23bc03ac8 · inbound

Humanity's Last Exam cites this paper.

Humanity's Last Exam Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:40:50.350304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 00418eaf-ba6c-4c13-b005-b4182b51cdd1 · inbound

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation cites this paper.

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T04:42:04.771929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d5932e34-fc2d-4149-bfda-417ff6e36dd9 · inbound

Quantifying Frontier LLM Capabilities for Container Sandbox Escape cites this paper.

Quantifying Frontier LLM Capabilities for Container Sandbox Escape Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T19:43:40.853518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0189277-b3d4-40eb-b3dc-9def2a74622a · inbound

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing cites this paper.

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 132

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:45:52.939979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3c7fb686-9676-4ddb-b92a-76b5e3a3191a · inbound

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills cites this paper.

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T16:40:51.515451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f31584-7ea9-41de-ab10-7890120d3c43 · inbound

AlphaEval: Evaluating Agents in Production cites this paper.

AlphaEval: Evaluating Agents in Production Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:45:58.817569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 670e3a77-f49b-4e6a-b904-6acda6aaf242 · inbound

Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks cites this paper.

Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:06:19.087529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 98a4d09b-b3c1-483c-8fd2-b68f5d949d6f · inbound

Can LLMs be Effective Code Contributors? A Study on Open-source Projects cites this paper.

Can LLMs be Effective Code Contributors? A Study on Open-source Projects Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:46:10.852344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation af10d1ef-b6f1-4213-8cdb-52e0b21494d8 · inbound

Dynamic Cyber Ranges cites this paper.

Dynamic Cyber Ranges Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T22:16:53.348658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 901fe0bd-f957-4028-ad60-c19de5e945c4 · inbound

Risk Reporting for Developers' Internal AI Model Use cites this paper.

Risk Reporting for Developers' Internal AI Model Use Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:16:16.399595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f3479441-714c-411a-b0ed-5fb2f8e5e57e · inbound

XekRung Technical Report cites this paper.

XekRung Technical Report Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T14:51:14.588143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6f2e4b70-ed75-4997-8ad4-4ded7d60ee4d · inbound

Trace: Unmasking AI Attack Agents Through Terminal Behavior Fingerprinting cites this paper.

Trace: Unmasking AI Attack Agents Through Terminal Behavior Fingerprinting Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:41:18.994757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8c487224-e811-4da9-89bd-d92904e4ba7f · inbound

Autonomous Adversary: Red-Teaming in the age of LLM cites this paper.

Autonomous Adversary: Red-Teaming in the age of LLM Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:26:10.508553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fb629ce5-673b-4c01-a4d6-b413708b2c71 · inbound

Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches cites this paper.

Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:31:11.685007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 056324e2-fb99-4104-b553-afcf4b86cac3 · inbound

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios cites this paper.

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T04:10:57.348437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f204818c-98b3-493f-ab84-07171811d024 · inbound

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World cites this paper.

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:16:27.972213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 24ac8b9d-0e14-4b24-9694-01757c5bc2be · inbound

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World cites this paper.

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T14:22:27.655588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f64bae-f5e2-4773-88c2-c67e3df1b3d2 · inbound

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications cites this paper.

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-19T23:32:52.563721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 33d9d0cc-241a-4c13-8df6-342a25d52c98 · inbound

Benchmarking Mythos-Linked Bug Rediscovery cites this paper.

Benchmarking Mythos-Linked Bug Rediscovery Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T23:17:57.552731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8584ade9-95b6-446c-bf9e-18902bde487f · inbound

DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows cites this paper.

DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T10:18:11.749362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 305c9254-29ad-43f3-8569-8b25cfa8cddf · inbound

HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection cites this paper.

HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T08:54:45.823514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7e042dcc-a9f5-4faf-8701-a82bb982bb3f · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:51:07.929199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 001041d1-9921-45e9-9866-f3db5b16d6ed · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:06:43.185520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0e1e3c4c-a3a3-4fc0-85fc-a7b7e84f2e31 · inbound

Cybersecurity AI (CAI) Dataset cites this paper.

Cybersecurity AI (CAI) Dataset Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:13:26.856759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ab106e19-42cb-47ed-b501-4f3b97b30ebf · inbound

Stateful Online Monitoring Catches Distributed Agent Attacks cites this paper.

Stateful Online Monitoring Catches Distributed Agent Attacks Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T19:56:11.064697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d56a6cf9-90bf-410a-b13a-6f3bd59e972b · inbound

An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios cites this paper.

An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:48:46.344299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 99c16f9a-1b02-49bb-b4e3-14ce6bf99e4a · inbound

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents cites this paper.

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T17:40:01.102907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f1e2d4fa-4aef-4e74-9e82-9d19555f84d9 · inbound

Direct Causation in International Humanitarian Law and the Challenge of AI-Mediated Civilian Cyber Operations cites this paper.

Direct Causation in International Humanitarian Law and the Challenge of AI-Mediated Civilian Cyber Operations Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:54:22.125038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b35eadfd-1caa-44b8-a2e7-2eb5d55a9303 · inbound

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction cites this paper.

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:08:21.502047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ef5f186d-bd5e-4b54-b7d1-5f3115183312 · inbound

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents cites this paper.

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-10T18:37:31.169937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 65c92e11-d7bc-443a-8ac8-4bfc8b6376c6 · inbound

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents cites this paper.

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T00:49:47.662275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ec7e9b-7c8e-48ae-9d35-a983f0fcfb48 · inbound

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents cites this paper.

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T23:44:37.323064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceff4a75-aac0-40df-b438-27b6d540f7d0 · inbound

Harmonizing AI Safety Thresholds cites this paper.

Harmonizing AI Safety Thresholds Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T21:24:15.880141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23646153-646d-483d-acfc-45130e22460a · inbound

RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery cites this paper.

RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T15:04:09.259606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911f64eb-a401-452b-86ca-d0fc8217fff4 · inbound

Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks cites this paper.

Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T06:49:26.953693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 579da816-ab2d-4ffb-98f7-0939b6df73a4 · inbound

The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play cites this paper.

The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T02:31:26.073853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c75942d-277b-4329-a925-2a8d7343f2de · inbound

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents cites this paper.

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T00:13:37.291705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.