Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 25, 2026Chicago, Illinois, USA

Evidentiary Gaps in AI Collusion Detection: When Price Patterns Are Not Enough

Sharon T. Itonyo · Team Evidence-Aware Collusion Audit

Submitted to AI Collusion Research Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Evidentiary Gaps in AI Collusion Detection: When Price Patterns Are Not Enough

Open in a new tab (opens in new tab)
Share

We investigate whether an AI-collusion auditor can distinguish deliberately coordinated pricing from innocent parallel behavior when monitoring evidence is incomplete.

Using independently generated synthetic pricing scenarios, we compare price-only detection with an evidence-aware classifier across different levels of audit visibility. The evidence-aware approach detects 159 of 160 planted coordination cases under complete evidence, compared with 70 of 160 for the price-only baseline.

However, a separate benign stress test reveals a critical limitation: when two independent sellers follow the same public price recommendation, the evidence-aware detector flags all 160 cases under complete visibility.

The findings show that strong detection performance does not automatically establish the cause of observed coordination. Reliable accountability requires evidence about the origins and meaning of suspicious behavior, not just a convincing detection score.

Reviews

Judging this Sprint?

Review “Evidentiary Gaps in AI Collusion Detection: When Price Patterns Are Not Enough”

Your public critique appears on the project page without your name. Reviews of strong projects are shared with funders, as you choose below.

Not shown on the project page.

Shown on the project page, without your name.

Only the Apart team reads this, and funders if you agree below.

Decline to score

Only when the quality of the writing makes the work impossible to follow. Say why in your private critique; the project page shows only that a judge declined, not why.

How much would this matter for the field if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.
Sharing your name *

When we share a strong project with funders, your name, scores and public critique go with it, confidentially; this choice is only about whether your name is public. If you think this project deserves funding, please also endorse it: that carries the most weight.

Share my private critique with funders *

See our Privacy Policy.

  1. A clear, careful write-up with honest limits and well-chosen negative controls (common cost shock, talk without action); the counts and percentages I checked are internally consistent. The public-bulletin stress test makes a valid point: an auditor that cannot see where a price target came from cannot tell public guidance from private agreement. However, the main results largely follow from how the generator was built, as the paper partly acknowledges: planted proposals are followed by matching prices by construction, so follow-through features separate them almost perfectly, and the bulletin is logged in the same field as private proposals, so a high flag rate on the stress test is expected by design. The sellers are scripted rather than LLMs and the code is not public, so the results cannot be checked independently. Next steps: run LLM pricing agents, add a provenance field and show it resolves the stress case, and release the script.

    Read full reviewShow less

Cite this project

@misc{itonyo2026evidentiary,
  title = {{Evidentiary Gaps in AI Collusion Detection: When Price Patterns Are Not Enough}},
  author = {Sharon T. Itonyo},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/evidentiary-gaps-in-ai-collusion-detection-when-price-patterns-are-not-enough-8t27}},
  url = {https://apartresearch.com/sprints/projects/evidentiary-gaps-in-ai-collusion-detection-when-price-patterns-are-not-enough-8t27}
}

More from AI Collusion Research Sprint

All 392 entriesBrowse all projects

A Sprint is running now

AI x Epistemics Research Sprint · Nov 13 - 15, 2026