Paper Citation Record · LEDGER

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards

As of 2 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2604.23341.

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

pith.paper-citation-record.v1
2604.23341 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T07:48:34.672171Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-02T06:30:47.504484+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

33 of 33 outbound references displayed

verified exact14
verified fuzzy18
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1cb94911-ffd9-4fe9-8c4b-587bee0278f2 · outbound

This paper cites A Multi-Task LLM Framework for Multimodal Speech-Based Mental Health Prediction.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards A Multi-Task LLM Framework for Multimodal Speech-Based Mental Health Prediction

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.893707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation c9d9dd6c-dcc4-4256-9a6b-1808a72a7348 · outbound

This paper cites Self-Reﬁ ned Generative Foundation Models for Wireless Trafﬁc Predicti on.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Self-Reﬁ ned Generative Foundation Models for Wireless Trafﬁc Predicti on

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.879919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation d610eb30-97ec-46f6-9c99-6950eb309c82 · outbound

This paper cites Reinforcement Lear ning- Guided Large Language Model Fine-Tuning for Privacy-Prese rving Text Rewriting.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Reinforcement Lear ning- Guided Large Language Model Fine-Tuning for Privacy-Prese rving Text Rewriting

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-08T22:49:21.823692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation bc445ca7-fefc-49d7-a050-f8e373f351df · outbound

This paper cites Large Language Models for Detecting Cyberat tacks on Smart Grid Protective Relays.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Large Language Models for Detecting Cyberat tacks on Smart Grid Protective Relays

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.869642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6f8b8a5f-da3b-4c4f-8196-18c8f6a33957 · outbound

This paper cites T owards explainable network intrusion detection using large langu age models.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards T owards explainable network intrusion detection using large langu age models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.080805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation f013e0bd-95d2-426a-9532-9b5056c6c007 · outbound

This paper cites Large language model for s mart in- verter cyber-attack detection via textual analysis of volt /var commands.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Large language model for s mart in- verter cyber-attack detection via textual analysis of volt /var commands

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.051596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 4907bf7a-3d02-44d3-8c23-f5def21f6135 · outbound

This paper cites Chatgpt an d other large language models for cybersecurity of smart grid applicatio ns.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Chatgpt an d other large language models for cybersecurity of smart grid applicatio ns

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.091944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation abf7a090-4ef5-4961-a055-47579eaa66c4 · outbound

This paper cites Analyzing Agent Collisions in AI-Aided Energy Management Systems.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Analyzing Agent Collisions in AI-Aided Energy Management Systems

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.086693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation b1560769-2646-40a5-8b2c-1c2007c10f41 · outbound

This paper cites Available: https://ieeexplore.ieee.org/document/11204591/.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Available: https://ieeexplore.ieee.org/document/11204591/

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.888685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 122938c6-0cd0-453a-b38c-5d1210935f55 · outbound

This paper cites Scene- aware non-intrusive load monitoring using large language m odels.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Scene- aware non-intrusive load monitoring using large language m odels

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.075886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 9bfec1d2-6d17-4164-a891-fbe2052fa609 · outbound

This paper cites Large Language Model-Based Framewor k for Explainable Cyberattack Detection in Automatic Generatio n Control Systems.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Large Language Model-Based Framewor k for Explainable Cyberattack Detection in Automatic Generatio n Control Systems

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.981633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 7c03e67c-3133-495e-96ac-ceb90df41383 · outbound

This paper cites A Privacy Policy Text Compliance Reasoning Framework with Large Language Models for Healthcare Services.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards A Privacy Policy Text Compliance Reasoning Framework with Large Language Models for Healthcare Services

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.955435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 1220277b-bdb3-4d48-b75f-5b327ef8efa2 · outbound

This paper cites Connecting Minds: AI Use Cas es to Bridge Power Systems and Large Language Models for Practica l Ap- plications.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Connecting Minds: AI Use Cas es to Bridge Power Systems and Large Language Models for Practica l Ap- plications

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.058486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation d903f09a-5387-4a3c-8f8b-fdc4cd4c636a · outbound

This paper cites egridgpt: Trustworthy ai in the control room.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards egridgpt: Trustworthy ai in the control room

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.139838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 70be0295-aa74-4717-893f-6757c3616adb · outbound

This paper cites Causality-aware llm-enhanced graph representation lear ning for adap- tive power system control.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Causality-aware llm-enhanced graph representation lear ning for adap- tive power system control

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.118100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6b29ed00-ba84-40b5-92e1-03a1aea4f8da · outbound

This paper cites Powergrap h-llm: Novel power grid graph embedding and optimization with large lang uage models.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Powergrap h-llm: Novel power grid graph embedding and optimization with large lang uage models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.054872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6b6ce2f2-9c44-4a82-a022-9127a1316c88 · outbound

This paper cites Jailbroken: H ow Does LLM Safety Training Fail?.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Jailbroken: H ow Does LLM Safety Training Fail?

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.073485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 18f4ce8e-3b62-4084-96e4-5179c817f098 · outbound

This paper cites Ge nerative AI and LLMs for critical infrastructure protection: evalua tion bench- marks, agentic AI, challenges, and opportunities.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Ge nerative AI and LLMs for critical infrastructure protection: evalua tion bench- marks, agentic AI, challenges, and opportunities

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.063394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 653d36c0-8089-4b23-b823-dfa40e5a3e24 · outbound

This paper cites BitBypass: A new direction in ja ilbreaking aligned large language models with bitstream camouﬂage.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards BitBypass: A new direction in ja ilbreaking aligned large language models with bitstream camouﬂage

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.110510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation e8f4e850-05ed-4c5c-ab90-86f91247be57 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:37:07.279605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation dbfa9a3b-0011-4d8c-b298-0130c8398706 · outbound

This paper cites CIP reliabil- ity standards.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards CIP reliabil- ity standards

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.135932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 5b361a69-f065-4f92-94ef-662394f30925 · outbound

This paper cites TOP reliability standards.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards TOP reliability standards

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.123083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 562e626a-f675-4875-bda0-b782495a4eb7 · outbound

This paper cites EOP reliability standards.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards EOP reliability standards

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.101275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 630025ea-df51-4e57-ac35-453d00c050b5 · outbound

This paper cites Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms

Reference 24

Resolution: verified exact; doi, observed 2026-05-08T22:49:21.836682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation d34c9a97-801c-4c8d-9286-994a0a74a662 · outbound

This paper cites Gpt-4o mini: advancing cost-efﬁcient intelligence.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Gpt-4o mini: advancing cost-efﬁcient intelligence

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.106291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation abd4a928-159f-49c7-a5df-cb18cf892ff1 · outbound

This paper cites Gemini 2.0 ﬂash-lite.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Gemini 2.0 ﬂash-lite

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.131854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 80c29067-1fdc-45d3-b6af-45dcb3385c56 · outbound

This paper cites Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T17:28:08.127864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation d8f54dfc-79ba-4e34-bf74-995086834521 · outbound

This paper cites Royal Society Open Science , author =.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Royal Society Open Science , author =

Reference 28

Resolution: metadata mismatch; doi, observed 2026-05-08T22:49:21.832456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6f808d18-3baa-45a6-9ba8-33e4825421d5 · outbound

This paper cites An Efﬁcient Finetuning Method for LLM generated text detection in Power Grid.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards An Efﬁcient Finetuning Method for LLM generated text detection in Power Grid

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.909645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 4b8c6b7b-2a55-4276-a43c-c2a5a255fe1c · outbound

This paper cites Applying Fine-tuned Large Language Model to Distribution System State Estimation.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Applying Fine-tuned Large Language Model to Distribution System State Estimation

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:11.015342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation e75da50a-60ba-4958-a71b-62d2fd5bdbd3 · outbound

This paper cites Robu st Electricity Theft Detection Against Data Poisoning Attacks in Smart Gri ds.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Robu st Electricity Theft Detection Against Data Poisoning Attacks in Smart Gri ds

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.927362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 6d86845d-f7b2-4e39-abac-3d02acf96e3b · outbound

This paper cites A Model-Independent Trojan Attack on Deep Learning-Based FD IA Detection in Smart Grid Protection Systems.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards A Model-Independent Trojan Attack on Deep Learning-Based FD IA Detection in Smart Grid Protection Systems

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.921345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation dc98acbd-006d-4356-9a4d-9b06cf790f8e · outbound

This paper cites Securing IoT Ma lware Classiﬁers: Dynamic Trigger-Based Attack and Mitigation.

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards Securing IoT Ma lware Classiﬁers: Dynamic Trigger-Based Attack and Mitigation

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:10.903923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Pith citing papers

No inbound Pith citation observations are available.