Paper Citation Record · LEDGER

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

As of 11 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 1 inbound Pith citation observation for arXiv:2606.05647.

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

pith.paper-citation-record.v1
2606.05647 v1

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T01:48:56.367899Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T12:50:00.612066Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

50 of 50 outbound references displayed

verified exact5
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch16

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c5cf12ac-2454-4d40-bc2c-7f7c10b1fa0f · outbound

This paper cites Information and Software Technology , pages=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Information and Software Technology , pages=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a75ae00e-f95c-4d12-bc1d-c850dd9a1104 · outbound

This paper cites and Yang, John and Wettig, Alexander and Yao, Shunyu and Pei, Kexin and Press, Ofir and Narasimhan, Karthik , booktitle =.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? and Yang, John and Wettig, Alexander and Yao, Shunyu and Pei, Kexin and Press, Ofir and Narasimhan, Karthik , booktitle =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cab7743-e59f-4e8a-ae1e-ee35058de401 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Advances in Neural Information Processing Systems , volume=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99045116-2597-43ba-aded-dc792c07ca4e · outbound

This paper cites ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models , booktitle =.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models , booktitle =

Reference 4

Resolution: verified exact; doi, observed 2026-06-28T01:51:28.890593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 36eb4624-5023-45bd-a2f4-158dd4183ff8 · outbound

This paper cites Retrieved from https://arxiv.org/abs/2512.14012.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Retrieved from https://arxiv.org/abs/2512.14012

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:46:57.264600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 71e53e0f-4dbb-4f5e-b36f-7a8e38b73c40 · outbound

This paper cites Horikawa, H.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Horikawa, H

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.281030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9b58cfe1-7e13-4a3b-a5d3-7ac32affe3c3 · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:57.283555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3849e3d0-15e6-4617-8d9b-78cc4f217974 · outbound

This paper cites Agents of Chaos.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Agents of Chaos

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:57.288595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 04ee2710-624d-4d15-a8ed-22a4121c84ff · outbound

This paper cites ICLR 2025 Workshop on Building Trust in Language Models and Applications , year=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? ICLR 2025 Workshop on Building Trust in Language Models and Applications , year=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724378d9-82a6-4909-9019-3b82872b7f95 · outbound

This paper cites Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems , pages=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems , pages=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f27775fe-bfa1-46bc-b86e-09ebca92eac6 · outbound

This paper cites How Does Information Access Affect LLM Monitors’ Ability to Detect Sabotage?.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? How Does Information Access Affect LLM Monitors’ Ability to Detect Sabotage?

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.278635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 548eac33-5415-4f56-bcf3-012132e23035 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:46:57.277907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2e3f7154-9cf2-4915-a185-ecdd0f8137fc · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2308a4c-3a33-43ff-b475-5079dedeaeb2 · outbound

This paper cites A Survey on Trustworthy.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? A Survey on Trustworthy

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89f16ad-0224-4d49-8727-66d5f4a3f87e · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5212ba0f-3037-41c2-86cc-a141e13a1a44 · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88c25f8e-ebc2-4222-bd8b-e495a781d2ea · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 158293f9-b2be-4a73-a15b-3f0466147936 · outbound

This paper cites 2025 , journal =.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? 2025 , journal =

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.286024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c5a38714-17ac-4b11-80ed-2ca7e4a0e4cb · outbound

This paper cites Async Control: Stress-Testing Asynchronous Control Measures for.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Async Control: Stress-Testing Asynchronous Control Measures for

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da168a9-a7f1-4ba9-97e3-4cedd4cbf827 · outbound

This paper cites Reliable Weak-to-Strong Monitoring of LLM Agents.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Reliable Weak-to-Strong Monitoring of LLM Agents

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:46:57.291196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation aec8c6f0-c3d2-4711-994f-4b029290bde2 · outbound

This paper cites 2025 , journal =.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? 2025 , journal =

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.264776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b61a4d78-074f-48f1-8ec3-94d54cc51402 · outbound

This paper cites Alignment faking in large language models.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Alignment faking in large language models

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:57.262186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6e3e06bf-5acd-4d39-b3e0-d68820c2c69b · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0715d350-1acc-43b0-a23c-ce60b0cebc9a · outbound

This paper cites Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:57.267236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0fcbb8f8-b50b-4ca2-8579-d9b1692feb33 · outbound

This paper cites Assessing.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Assessing

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9e179ad-05c4-47b9-b70a-252c895875c4 · outbound

This paper cites Ritchie, Soren Mindermann, Evan Hubinger, Ethan Perez, and Kevin Troy.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Ritchie, Soren Mindermann, Evan Hubinger, Ethan Perez, and Kevin Troy

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.269807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4371d167-04c8-4802-bea1-f30afd6ec100 · outbound

This paper cites Natural Emergent Misalignment from Reward Hacking in Production.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Natural Emergent Misalignment from Reward Hacking in Production

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f27233-de57-462a-bd99-04576628c8c3 · outbound

This paper cites Stress Testing Deliberative Alignment for Anti-Scheming Training , url =.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Stress Testing Deliberative Alignment for Anti-Scheming Training , url =

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.259807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 73d7b82c-4499-4dc7-8ff0-f4c9ac8f398a · outbound

This paper cites , journal =.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? , journal =

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3459a6-c672-4bbe-a28f-7c0f62a61807 · outbound

This paper cites Cot red-handed: Stress testing chain- of-thought monitoring.ArXiv, abs/2505.23575.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Cot red-handed: Stress testing chain- of-thought monitoring.ArXiv, abs/2505.23575

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.253840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5a8ca333-d64e-4da0-8a1b-3c54ac3a2859 · outbound

This paper cites When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9adf27e-512e-4567-acbb-1d32dd378503 · outbound

This paper cites Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:46:57.248117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 562f5cc0-a16f-41c5-b069-98ae9fa55e2c · outbound

This paper cites Is Vibe Coding Safe?.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Is Vibe Coding Safe?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d336efa8-bfa0-4201-95aa-e1fe95390763 · outbound

This paper cites Maloyan and D.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Maloyan and D

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.293745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e7d06ee2-51e1-4aed-b1ab-d7a163826097 · outbound

This paper cites Evolution of Programmers' Trust in Generative.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Evolution of Programmers' Trust in Generative

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73db284a-fb6e-4af1-9535-ac8873cb59d4 · outbound

This paper cites Privacy Leakage Overshadowed by Views of.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Privacy Leakage Overshadowed by Views of

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49fa82c2-df53-4912-87c2-0ec106798590 · outbound

This paper cites Not What You've Signed Up For: Compromising Real-World.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Not What You've Signed Up For: Compromising Real-World

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a6e55f6-a435-42f7-9429-14e3cbb5b190 · outbound

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

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Frontier Models are Capable of In-context Scheming

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:57.251299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fb42a312-2899-4dcb-b526-a34d427c02b4 · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 39

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:57.256904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c970b384-e342-48b3-9543-cc33e94b987e · outbound

This paper cites Asleep at the Keyboard?.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Asleep at the Keyboard?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bf517bd-ef18-433c-bd76-7d65558826ff · outbound

This paper cites Do Users Write More Insecure Code with.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Do Users Write More Insecure Code with

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 718e5478-0239-4c92-a815-0fedbc601566 · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61d1e8d-b559-4a7e-ad9c-761dd17e43f1 · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5fd8cd-7c50-489c-8cc6-e171ff683a6e · outbound

This paper cites Red-Teaming.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Red-Teaming

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87090d60-508a-47b2-9f36-0551a4e07d2d · outbound

This paper cites an unresolved cited work.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e11dc3fa-c38d-40ae-a0d0-364508b3e5ec · outbound

This paper cites SafeArena: Evaluating the Safety of Autonomous Web Agents.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? SafeArena: Evaluating the Safety of Autonomous Web Agents

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.272709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 23b73752-0f46-4c3a-93ef-24e996d857f1 · outbound

This paper cites Usability evaluation in industry , volume=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Usability evaluation in industry , volume=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28eb45e3-cc5b-416f-afe9-da1d99c19e17 · outbound

This paper cites Sabotage Evaluations for Frontier Models.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Sabotage Evaluations for Frontier Models

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:46:57.283112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 92df3bc5-d35e-492c-a519-d8c4b080cffe · outbound

This paper cites Authorea Preprints , year=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Authorea Preprints , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7f1493-42fe-4fb4-8f06-7c2896a09bd2 · outbound

This paper cites IEEE Access , volume=.

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? IEEE Access , volume=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-28T01:48:56.367899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d684a475-b17e-4e4b-977a-6aac26fb3534 · inbound

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D cites this paper.

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T12:50:00.612066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.