Paper Citation Record · LEDGER

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 36 inbound Pith citation observations for arXiv:2504.15585.

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

pith.paper-citation-record.v1
2504.15585 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 36 of 36 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:04:08.645670Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation f81e63ee-310a-4b40-a780-cc2cec28daae · inbound

Adaptive Backtracking for Privacy Protection in Large Language Models cites this paper.

Adaptive Backtracking for Privacy Protection in Large Language Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T23:04:08.645670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8360dd42-bfa8-4b80-8ac4-5808aa6baa3c · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T10:38:58.402887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dcbcab6-57cf-46f6-b4f6-c7ef91578aa5 · inbound

KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis cites this paper.

KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-05T10:21:47.149354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627e0278-77d1-45ca-b4ff-497df50cc0d9 · inbound

Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial cites this paper.

Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 175

Resolution: unresolved; no resolver link, observed 2026-08-05T04:50:32.170105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5687e63f-1cfc-491f-8ddc-4cba96ebfa15 · inbound

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence cites this paper.

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:50.674982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3004583b-014b-4f1f-a1fb-04940e398556 · inbound

Agentic Services Computing cites this paper.

Agentic Services Computing A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 178

Resolution: unresolved; no resolver link, observed 2026-08-04T14:41:50.921051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa5d3d6-f2b3-4950-8354-f4c2c0d9357f · inbound

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models cites this paper.

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:36:22.463634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ccd089e-dbac-49e9-896e-a4b7c58c5b3e · inbound

Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety cites this paper.

Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T09:15:21.818144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f81fcd7-473e-4ead-8dca-e4c2f59e4af5 · inbound

Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation cites this paper.

Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T08:44:56.504049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8990c204-c015-4c3a-bd3e-0608db533c45 · inbound

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs cites this paper.

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:00:30.397180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 432e8ebe-e187-4091-93ad-ae6b1c7facf7 · inbound

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer cites this paper.

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T06:23:43.757957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746a367d-6d75-4b97-850f-e419c3b57eb1 · inbound

ProbeLLM: Automating Principled Diagnosis of LLM Failures cites this paper.

ProbeLLM: Automating Principled Diagnosis of LLM Failures A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T23:43:07.687190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4125b05d-325a-465f-9376-34ee1f85469b · inbound

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems cites this paper.

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:16:04.234442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e74ea2e4-43ec-46d2-ac23-36da4267756b · inbound

BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models cites this paper.

BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:21:00.645817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1e41d869-3c91-4f07-b6bc-d6471d446470 · inbound

LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review cites this paper.

LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:56:33.814418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 93e9fd91-8f12-4b4d-acc2-50be6e16a428 · inbound

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety cites this paper.

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 178

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:05.697693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9297d37a-a513-4dcd-8b8d-0d9f71da619c · inbound

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning cites this paper.

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:26:29.219146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5b14aa25-c446-4733-8b09-f9ad1b3e762e · inbound

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment cites this paper.

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:21:07.319493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0536dfdb-3e49-4208-97fc-b63d716f6d09 · inbound

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cites this paper.

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:07:00.563071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0eb13ae8-32e2-4dc7-8a0b-27627098488d · inbound

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cites this paper.

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:12:58.976961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a6dfaaca-478c-4429-bd9a-077cbb8d879f · inbound

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models cites this paper.

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:02:58.891963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9a3344e2-5e67-4e03-bc5a-0669f6456152 · inbound

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cites this paper.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.850450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1ebf339c-e46d-4d65-addf-a2d9d2dc71a7 · inbound

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook cites this paper.

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:39:49.124688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 49e329d1-315d-45f4-a7b7-b335c0985d17 · inbound

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs cites this paper.

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-21T04:49:35.654769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 063b7fbf-a09c-4ef6-82f4-5e3ceab79311 · inbound

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy cites this paper.

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:53:59.521103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a1cdd3b8-337d-4c90-95a3-6dd4ab19b69b · inbound

Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization cites this paper.

Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:43:13.502152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation df30c543-00b4-46cf-9de7-8d4e668bdb15 · inbound

POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems cites this paper.

POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T23:06:19.985654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aaa70230-6616-4e55-ad12-b59207d03a12 · inbound

Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation cites this paper.

Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:56:56.715862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 090f64dc-976d-4b53-b52f-a84b53fc51b1 · inbound

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation cites this paper.

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 182

Resolution: verified exact; arxiv_id, observed 2026-06-27T13:20:56.866720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7b03d879-f0ea-47f2-8cf2-a175c1c308fc · inbound

SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems cites this paper.

SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:28:18.834488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ef2b4891-04f4-4c96-a460-7e69a64d9593 · inbound

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models cites this paper.

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T19:40:06.706686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b1fc6796-572d-4c6b-b90d-f88057d94645 · inbound

Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints cites this paper.

Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T08:05:31.326711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 44eabc72-7363-4262-a7ca-ec27128cfdb2 · inbound

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors cites this paper.

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-06-30T08:04:28.739091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation baf5f170-7c2e-4782-985c-c1ae06ee600f · inbound

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors cites this paper.

Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T04:39:06.922277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc0892e-e9c5-4435-a09e-b5039a8bd066 · inbound

Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents cites this paper.

Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-14T11:21:48.935912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f185a3e-dd8e-4ffa-9144-a44a7613bf20 · inbound

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models cites this paper.

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 185

Resolution: unresolved; no resolver link, observed 2026-08-01T19:02:48.799933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.