Paper Citation Record · LEDGER

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

As of 5 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2607.25255.

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

pith.paper-citation-record.v1
2607.25255 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T03:01:05.389645Z

measured 35 of 35 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 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

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 066969e4-8889-46a2-b97e-aabf0f8f8d0b · outbound

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

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:00.491588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f1666b0-e8c7-4fa2-bf80-39bf185725eb · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:00.630371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe15aace-9116-4236-aa6d-637c86ca64dd · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:00.838366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e36e562f-73f1-44d4-a8a8-33a128893b08 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:00.962750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d748325b-4b90-4ad3-a6e2-69d717db0aac · outbound

This paper cites AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.020484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 293a6212-7cae-4f9a-bf56-d3a53af48d8c · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.131934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc248440-8903-4c91-8319-0071d7664af5 · outbound

This paper cites DeepSeek-V3 Technical Report.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems DeepSeek-V3 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.247000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34280382-9616-46d8-b7ec-49d0427262b9 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.313298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e93ebdc-df34-4b66-909b-06179305ff7c · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.426335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45adbf7-a929-46a2-bd20-80ffd076bf88 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.550580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe653cec-59e1-4204-9013-de8bc7bb1dc5 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.680381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d64364-72c8-42fe-99cd-3a3e45a42e8e · outbound

This paper cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.805934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 912ed7b9-016b-4fce-9974-e97950e448cf · outbound

This paper cites A Cross-Language Investigation into Jailbreak Attacks in Large Language Models.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:01.988072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ab0a1e-1c48-4ba9-9a15-49ccdcc26d1d · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.119512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b346df-229d-489f-9424-29b16b243bac · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.242076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d7fba9-6cea-4ccf-9030-c4bc1f3501c3 · outbound

This paper cites GPT-4 Technical Report.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems GPT-4 Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.384615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 561650cf-bdc5-41c9-b9ea-e780f86727a4 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.548190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 778a313e-bf1c-4547-99e9-df1fa662b2b1 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.619357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d5fb7a-1ede-4a71-952c-b7357b8eb434 · outbound

This paper cites Training language models to follow instructions with human feedback.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Training language models to follow instructions with human feedback

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.734309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30e0b61e-2ddb-4a4f-9026-b14fcee85269 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.860086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf6ef56-52df-4eff-b7d9-c0c80cfeb583 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:02.988488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0c6a3eb-3c6b-42e6-866c-4c204793b528 · outbound

This paper cites A.; Gaonkar, R.; K "o pf, B.; Krueger, D.; Paverd, A.; Salem, A.; and Tople, S.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems A.; Gaonkar, R.; K "o pf, B.; Krueger, D.; Paverd, A.; Salem, A.; and Tople, S

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:03.123330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04d54f6b-26d3-4148-ba7e-bbcc254877bb · outbound

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

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems SafeArena: Evaluating the Safety of Autonomous Web Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:03.238335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54fdaf2a-c775-4439-8156-113f4b5717cd · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:03.365133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08e16c96-760e-4749-b5b6-7c746557bd35 · outbound

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

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Jailbroken: How Does LLM Safety Training Fail?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:03.521920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04b0c34c-11b1-404b-9dd2-c9c33f9b7eb3 · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:03.706227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f324083-61a9-49fd-ad26-d21ce208bb9a · outbound

This paper cites GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:03.860989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a8848c-ae84-4d76-9797-0dc8b9248b6d · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:04.023412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968cd385-199c-4a28-8081-ba26bce3f4c8 · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:04.184802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78b05626-083e-41d5-9820-3a15e1871edf · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:04.342402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bffc5fb4-8ec2-44ca-99ab-d85f78907be9 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:04.510093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df871845-a3d4-4bf0-a2d3-dd431ad15d7c · outbound

This paper cites AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:04.706186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf33890-f0bd-4a1b-9675-fcbf3357c1a8 · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:04.949244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0446b82c-6a33-41d9-ba8f-5264c7d0aa8a · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:05.124812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b6b8b8-1a2c-4ccd-9c92-ea64c5ef64eb · outbound

This paper cites an unresolved cited work.

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T03:01:05.389645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.