Paper Citation Record · LEDGER

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

As of 23 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 8 inbound Pith citation observations for arXiv:2506.07564.

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

pith.paper-citation-record.v1
2506.07564 v3

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:36:34.199007Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:34:44.587519Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T15:47:06.375467Z

Reference resolution

26 of 26 outbound references displayed

verified exact1
verified fuzzy9
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 02e4b38f-6e83-40d0-80f9-8b7a875f75a6 · outbound

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

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.083647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867840f8-c500-49dd-b04d-49a72c2b71d4 · outbound

This paper cites Langchain – building applications with llms.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Langchain – building applications with llms

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.903769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a6d4c4c7-22ca-4e4f-869c-cb37d3e2535e · outbound

This paper cites Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.098762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc3f983-13cc-4795-8e5a-ddd4f7ba557f · outbound

This paper cites an unresolved cited work.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.102956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 580d78ba-5d7d-4274-893f-bf5869c5899b · outbound

This paper cites Hacking auto-gpt and escaping its docker container.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Hacking auto-gpt and escaping its docker container

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.889641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f1403ac6-258d-4f8d-a109-3e0b5bcdbe2c · outbound

This paper cites VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.112634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dca09ba2-4916-402f-8b24-c890973affff · outbound

This paper cites ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.117425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2604efad-cd46-4739-8285-e2d38c17fe1d · outbound

This paper cites AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.121835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0846099e-9cf3-412a-a190-b6970d5d2703 · outbound

This paper cites Toward the unification of generative and discriminative visual foundation model: A survey.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Toward the unification of generative and discriminative visual foundation model: A survey

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.874753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3213c82-0bb8-458a-b9de-f90621fd591a · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.130937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb8a6f5-3751-46f6-9655-2dd0297a3825 · outbound

This paper cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.135801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512184cf-1507-4049-890f-a2bee3347c39 · outbound

This paper cites Permissive information-flow analysis for large language models, 2024.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Permissive information-flow analysis for large language models, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.140246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbdac69-1fc8-4525-b5c1-4d8b028ef217 · outbound

This paper cites Eqdrive: Efficient equivariant motion forecasting with multi-modality for autonomous driving.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Eqdrive: Efficient equivariant motion forecasting with multi-modality for autonomous driving

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.859325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b9fb2683-9f90-4b50-a10c-3e9be962363b · outbound

This paper cites Equivariant map and agent geometry for autonomous driving motion prediction.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Equivariant map and agent geometry for autonomous driving motion prediction

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.839166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5bb1352a-c668-4354-8779-00586cbb3ef6 · outbound

This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems OpenVLA: An Open-Source Vision-Language-Action Model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.152856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23c7da1f-00ef-428d-8bf9-2fd2c5649d30 · outbound

This paper cites Cmp: Cooperative motion prediction with multi-agent communication.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Cmp: Cooperative motion prediction with multi-agent communication

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.823325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ae5ad172-0a59-4604-b2fd-f62ea0cd1d83 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.161342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36414a03-35c5-4a86-a167-64044d85995c · outbound

This paper cites A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.165591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c613a0f6-f325-42f6-b2e5-3267395f76f9 · outbound

This paper cites Autotrust: Benchmarking trustworthiness in large vision-language models for autonomous driving.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Autotrust: Benchmarking trustworthiness in large vision-language models for autonomous driving

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.170319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df1932c0-11f8-487a-91e9-96b516bf6850 · outbound

This paper cites Openemma: Open-source multimodal model for end-to-end autonomous driving.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Openemma: Open-source multimodal model for end-to-end autonomous driving

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.808635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 862f3ffc-dbb3-453e-91c2-3a5559d9bc60 · outbound

This paper cites Can Large Vision Language Models Read Maps Like a Human?.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Can Large Vision Language Models Read Maps Like a Human?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.178330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a32f2e2d-85ab-4bfe-8340-176799eb69c4 · outbound

This paper cites Re-align: Aligning vision language models via retrieval-augmented direct preference optimization, 2025 c.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Re-align: Aligning vision language models via retrieval-augmented direct preference optimization, 2025 c

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.182886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f70d8678-77a2-4caf-97d0-8ff2c9e760bf · outbound

This paper cites MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:36:34.186965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d2cd3b8-3355-4381-ad28-fe3d4d98f635 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems React: Synergizing reasoning and acting in language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.794273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d52fafae-3f17-4fe8-9315-4cc3c097162d · outbound

This paper cites Point set voting for partial point cloud analysis.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Point set voting for partial point cloud analysis

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:36:34.779590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 616184ee-be0a-4240-8922-360e0aeaa69a · outbound

This paper cites Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation.

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:36:34.242390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation bc87b385-4161-41bc-9d2f-772844c2d8a8 · inbound

Demystifying the Visual Quality Paradox in Multimodal Large Language Models cites this paper.

Demystifying the Visual Quality Paradox in Multimodal Large Language Models SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:56:38.109741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 617d7038-2fd2-478c-aa7e-ffcfb5e373da · inbound

Reframing LLM Agent Security as an Agent-Human Interaction Problem cites this paper.

Reframing LLM Agent Security as an Agent-Human Interaction Problem SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:54:43.868238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 877db28d-6fe4-4be9-8265-2808e46409e0 · inbound

REPOT: Recoverable Program-of-Thought via Checkpoint Repair cites this paper.

REPOT: Recoverable Program-of-Thought via Checkpoint Repair SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T06:23:08.688382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5fcfe987-81ef-43d8-b75b-bd94beffa51d · inbound

Data Flow Control: Data Safety Policies for AI Agents cites this paper.

Data Flow Control: Data Safety Policies for AI Agents SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:47:06.376939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d6a97c80-1160-4293-bf75-fb59043903b0 · inbound

Data Leakage Prevention in Agentic Applications via Preemptive Hardening cites this paper.

Data Leakage Prevention in Agentic Applications via Preemptive Hardening SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:22.450766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23e62210-14b9-483b-b482-b434f548ad62 · inbound

MemTX: Transactional Belief Commit for Stateful Agent Memory cites this paper.

MemTX: Transactional Belief Commit for Stateful Agent Memory SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T23:36:16.579971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6649b84-ae81-41ed-84a1-a700785e8f75 · inbound

HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution cites this paper.

HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T15:34:44.587519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c5ba55c-ce98-48bc-8877-1d782033837c · inbound

CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents cites this paper.

CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:14.921424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.