Paper Citation Record · LEDGER

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach

As of 14 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2608.02698.

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

pith.paper-citation-record.v1
2608.02698 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:15:14.472934Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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 fuzzy24
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation daeea94b-e5bf-4d8f-bd81-5d2dc429bfb2 · outbound

This paper cites Multi-Agent Risks from Advanced AI.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Multi-Agent Risks from Advanced AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.328265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6da5944f-8752-4ab4-80c3-05277a47d31c · outbound

This paper cites Large language model based multi-agents: A survey of progress and challenges,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Large language model based multi-agents: A survey of progress and challenges,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.087533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7aa97816-b0df-4534-aaa5-4eb0e057df80 · outbound

This paper cites Secret collusion among AI agents: Multi-agent deception via steganography,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Secret collusion among AI agents: Multi-agent deception via steganography,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.074690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 79297a0b-abf9-479d-b8b0-67c907a04bcb · outbound

This paper cites Hidden in plain text: Emergence and mitigation of steganographic collusion in LLMs,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Hidden in plain text: Emergence and mitigation of steganographic collusion in LLMs,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.059551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4328301d-db56-4dd0-a6e9-2b8f83da3cb6 · outbound

This paper cites The prisoners’ problem and the subliminal channel,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach The prisoners’ problem and the subliminal channel,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.047269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f764d5e2-1597-405b-9630-6d99b24f4682 · outbound

This paper cites An information-theoretic model for steganography,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach An information-theoretic model for steganography,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.034641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d9dae784-820b-4285-8719-fcb9f0d17281 · outbound

This paper cites Information-theoretic analysis of information hiding,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Information-theoretic analysis of information hiding,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.354964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a41e6fc3-0f71-46bd-a3f3-295ac89e6bca · outbound

This paper cites RNN-Stega: Linguistic steganography based on recurrent neural net- works,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach RNN-Stega: Linguistic steganography based on recurrent neural net- works,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.014761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a0f5a16c-cc4a-400b-ab32-786dd45e522d · outbound

This paper cites An effective linguistic steganalysis framework based on hierarchical mutual learning,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach An effective linguistic steganalysis framework based on hierarchical mutual learning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:15.002819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f1082487-7e1b-4efe-aff9-9598b1a9e8b3 · outbound

This paper cites Intelligent agents: Theory and practice,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Intelligent agents: Theory and practice,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.368290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb69540-080f-4605-a230-8b05f03f40a4 · outbound

This paper cites Generative agents: Interactive simulacra of human behavior,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Generative agents: Interactive simulacra of human behavior,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.980556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 173aac8a-c0c7-4d8e-aca4-7a05d94d4b96 · outbound

This paper cites Pattern-based survey and categorization of network covert-channel techniques,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Pattern-based survey and categorization of network covert-channel techniques,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.968197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ed2a91c2-1b01-424a-be40-db5664aff833 · outbound

This paper cites A watermark for large language models,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach A watermark for large language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.955464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 60243195-9e61-4715-8491-1cb60ee98bf4 · outbound

This paper cites A survey of text watermarking in the era of large language models,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach A survey of text watermarking in the era of large language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.943996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 20544804-ee5a-4fa2-b45e-3832ca1d8783 · outbound

This paper cites Para- phrasing evades detectors of AI-generated text, but retrieval is an effec- tive defense,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Para- phrasing evades detectors of AI-generated text, but retrieval is an effec- tive defense,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.932075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 324692ac-d55e-4b31-b665-bcbb6218aab1 · outbound

This paper cites zkLLM: Zero knowledge proofs for large language models,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach zkLLM: Zero knowledge proofs for large language models,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.919630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f3cc319c-1ec4-45ca-a72e-ca2a38fafafb · outbound

This paper cites Learning to communicate with deep multi-agent reinforcement learning,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Learning to communicate with deep multi-agent reinforcement learning,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.907728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e4abb7ac-f8c2-4e05-af50-6c1eac574d14 · outbound

This paper cites Multi-agent cooper- ation and the emergence of (natural) language,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Multi-agent cooper- ation and the emergence of (natural) language,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.894791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9d22ac1a-6611-4821-a5b0-957868d54f08 · outbound

This paper cites AI control: Improving safety despite intentional subversion,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach AI control: Improving safety despite intentional subversion,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.882013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ea76d5d-84ec-475c-a2f8-3f4559dc63b6 · outbound

This paper cites Visibility into AI agents,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Visibility into AI agents,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.868770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 287c528b-baf2-44a2-83ff-b2e42f62e8f1 · outbound

This paper cites Infrastructure for AI Agents.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Infrastructure for AI Agents

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.412079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af45ebac-2a70-4b67-b2b8-9358b290a147 · outbound

This paper cites IDs for AI Systems.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach IDs for AI Systems

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.416295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c931faa2-a597-46b5-9cfc-4e0354362e27 · outbound

This paper cites Open Problems in Cooperative AI.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Open Problems in Cooperative AI

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.421439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c76fdcfa-ca6e-4ad8-819b-654a9a90403b · outbound

This paper cites Agent smith: A single image can jailbreak one million multimodal LLM agents exponentially fast,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Agent smith: A single image can jailbreak one million multimodal LLM agents exponentially fast,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.856156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 839b23aa-77aa-4e12-9014-371885a6fb0d · outbound

This paper cites Prompt infection: LLM-to-LLM prompt injection within multi-agent systems,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Prompt infection: LLM-to-LLM prompt injection within multi-agent systems,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.842672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 18d8a218-8c47-4d9b-971e-ec97bfe35daa · outbound

This paper cites Breaking the protocol: Security analysis of the model context protocol specification and prompt injection vulnerabil- ities in tool-integrated LLM agents,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Breaking the protocol: Security analysis of the model context protocol specification and prompt injection vulnerabil- ities in tool-integrated LLM agents,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.434501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51634323-89e7-4671-936f-c87d16fed01a · outbound

This paper cites Audit the whisper: Detecting steganographic collusion in multi-agent LLMs,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Audit the whisper: Detecting steganographic collusion in multi-agent LLMs,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.438222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3dacf19-ec33-4ab9-bece-8a3f71906e6e · outbound

This paper cites Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.442066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb60b5c3-2ab9-401b-a2d7-6e9a5b38d1d5 · outbound

This paper cites Detecting Multi-Agent Collusion Through Multi-Agent Interpretability.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.446045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30eb4b82-2534-4ac5-98b2-4a61b3096639 · outbound

This paper cites Mutual information neural estimation,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Mutual information neural estimation,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.827693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c8f3c45c-4fa9-4e4d-9121-da49b543960d · outbound

This paper cites Deep reinforcement learning that matters,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Deep reinforcement learning that matters,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.812864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dae66596-921c-4740-9637-08710195e46f · outbound

This paper cites Estimating mutual information,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Estimating mutual information,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.799525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a5692955-bac3-4e97-b9c8-6933cc659867 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Representation Learning with Contrastive Predictive Coding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:14.463718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b8f0e8-2bc4-42cf-a242-ad85f649037e · outbound

This paper cites CLUB: A contrastive log-ratio upper bound of mutual information,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach CLUB: A contrastive log-ratio upper bound of mutual information,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.785303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 64b7cf3c-ae0b-4f6a-909c-88ae1fea578a · outbound

This paper cites On variational bounds of mutual information,.

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach On variational bounds of mutual information,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:14.768668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

No inbound Pith citation observations are available.