Paper Citation Record · LEDGER

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment

As of 4 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2605.01147.

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

pith.paper-citation-record.v1
2605.01147 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-09T18:52:20.446029Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-19T21:28:00.370745Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-19T21:32:48.029692Z

Reference resolution

35 of 35 outbound references displayed

verified exact4
verified fuzzy22
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch7

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0a56a2cd-125e-4a50-9953-45e3b5e5ecdb · outbound

This paper cites International Conference on Learning Representations , year=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment International Conference on Learning Representations , year=

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.317639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ebeb4d4b-1c22-42b3-8890-8c67745dd2ba · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment On the Opportunities and Risks of Foundation Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T16:01:23.110281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b942913a-82fc-41f6-8c84-d3b0c1fc80b9 · outbound

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

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Advances in Neural Information Processing Systems , year=

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.313720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 57c5aff8-4d02-4963-9aec-bc7f3649671c · outbound

This paper cites 2025 , note=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment 2025 , note=

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.397603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6ea8e508-6502-4a5c-800a-eccea3945feb · outbound

This paper cites Review of Economic Studies , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Review of Economic Studies , volume=

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.344131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 92d8ad83-e1a0-4d76-8a9d-6b2639d50c98 · outbound

This paper cites Advances in Complex Systems , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Advances in Complex Systems , volume=

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.379643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 51a54f95-2fe9-4150-b19d-4afb4e4716d1 · outbound

This paper cites American Economic Journal: Microeconomics , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment American Economic Journal: Microeconomics , volume=

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.383416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b517c27c-1d96-4ac0-a34a-5ea14d3efdd2 · outbound

This paper cites Journal of Artificial Societies and Social Simulation , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Journal of Artificial Societies and Social Simulation , volume=

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.386965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d55d4303-55f0-4485-ac7f-1d23bfa04abc · outbound

This paper cites Beyond Single- Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Beyond Single- Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:01:23.077044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e9ef26ad-cb67-4309-b4bf-a45bdaef55d1 · outbound

This paper cites Scaling Laws for Neural Language Models.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Scaling Laws for Neural Language Models

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T16:01:23.117964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 87b472d4-b840-4891-898f-cdf7462ff619 · outbound

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

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Advances in Neural Information Processing Systems , year=

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.369547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5bc394d0-a237-4f38-a81f-9734e882ff89 · outbound

This paper cites Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:01:23.068855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bc219cbd-b587-44a1-9e96-8ee20b4d195c · outbound

This paper cites On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:01:23.128185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 51ca6e36-e80e-4597-89f1-b2fc3a1713a7 · outbound

This paper cites Journal of Political Economy , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Journal of Political Economy , volume=

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.377880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6576973f-7e2a-4209-a686-e8fcf1a6611b · outbound

This paper cites Quarterly Journal of Economics , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Quarterly Journal of Economics , volume=

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.382425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8cf6ad66-fc08-4913-b7a1-7babfd44e827 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T16:01:23.055824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 786c3f16-6a99-441e-ae32-0203b206af04 · outbound

This paper cites Some optimality conditions of set-valued optimization problems in locally convex topological vector spaces.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Some optimality conditions of set-valued optimization problems in locally convex topological vector spaces

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:01:23.093897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation de4297e0-d88c-4d5d-bda8-420dd0d3d605 · outbound

This paper cites ACM UIST , year=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment ACM UIST , year=

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.386619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation de72e922-3924-4223-ad09-06ed3fb7de76 · outbound

This paper cites Connection of event shapes to the heavy-flavor baryon enhancement.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Connection of event shapes to the heavy-flavor baryon enhancement

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:01:23.102141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 97f87e12-d8f1-412c-801a-7985dbddd211 · outbound

This paper cites Proceedings of the IEEE , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Proceedings of the IEEE , volume=

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.339113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3404dbe6-f1cc-4713-ae6b-fae47bee502c · outbound

This paper cites an unresolved cited work.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:37:13.315176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b40470db-25ea-4b13-962a-85c281fcde08 · outbound

This paper cites Journal of the American Statistical Association , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Journal of the American Statistical Association , volume=

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.347852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6fa765d7-1b61-4c03-92a7-00d70e2595e1 · outbound

This paper cites an unresolved cited work.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-05-25T22:37:13.351568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9f088397-1d39-4f3b-ae86-1d6ce9dd08a7 · outbound

This paper cites A Survey on LLM-as-a-Judge.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment A Survey on LLM-as-a-Judge

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T16:01:23.136941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cec8ee96-e03b-4146-8791-e3a9be3fb267 · outbound

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

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Advances in Neural Information Processing Systems , year=

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.374388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d2004ae6-f38e-471d-af04-ce7dd67ad1af · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Constitutional AI: Harmlessness from AI Feedback

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T16:01:23.083055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c380718d-7476-43bb-b8c6-b78599501e22 · outbound

This paper cites Transactions on Machine Learning Research , year=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Transactions on Machine Learning Research , year=

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.390417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9ca34bbb-f1f7-4e88-804f-461066bc032b · outbound

This paper cites Proceedings of the 2017 ACM Conference on Economics and Computation , pages=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Proceedings of the 2017 ACM Conference on Economics and Computation , pages=

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.394128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fdc19757-d2ef-4a04-86d5-dcd4411e9e08 · outbound

This paper cites Artificial Intelligence , volume=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Artificial Intelligence , volume=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.358444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 21a2a2a5-1dee-410f-9675-022cb1040892 · outbound

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

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Advances in Neural Information Processing Systems , year=

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.337308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c222367c-383c-4e92-9227-60e040a02d08 · outbound

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

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Advances in Neural Information Processing Systems , volume=

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.346829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b22eb6c7-1045-4a68-be3d-7c0de80edfc4 · outbound

This paper cites Improving Multi-Agent Debate with Sparse Communication Topology.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Improving Multi-Agent Debate with Sparse Communication Topology

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:01:23.050118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5faf6cce-3fd3-4a93-a6f4-58e51a1a8132 · outbound

This paper cites Transactions on Machine Learning Research , year=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Transactions on Machine Learning Research , year=

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.328892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e5de4911-54b1-402d-a940-43f94ddaf395 · outbound

This paper cites Transactions on Machine Learning Research , year=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Transactions on Machine Learning Research , year=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.343015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1751afee-fc8b-4e71-bb56-1e89bdc10552 · outbound

This paper cites Proceedings of the Conference on Fairness, Accountability, and Transparency , pages=.

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment Proceedings of the Conference on Fairness, Accountability, and Transparency , pages=

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T22:37:13.350555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 71dc3996-4629-4af3-8c99-c7e592cd8ef3 · inbound

State Contamination in Memory-Augmented LLM Agents cites this paper.

State Contamination in Memory-Augmented LLM Agents Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-19T21:32:48.031465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.