Skip to content
Apart Research
Apart Research
Contact us
Sprint projectOct 26, 2026Hyderabad, India

What the released Stego activations contain: an extraction-boundary audit of NARCBench

Saman Seshadri

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

Read the report

Report: What the released Stego activations contain: an extraction-boundary audit of NARCBench

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

Activation-based monitors are a proposed defense against covert collusion between AI agents, and benchmark claims about them depend on an assumption that is rarely checked: that the released activations were extracted from the inputs the paper describes. We audit that extraction boundary in NARCBench, a multi-agent collusion benchmark with a steganographic (Stego) scenario, using only the authors' released code and artifacts. Running the source's loader and tokenizing its output reproduces every released Stego token count exactly (1,320 of 1,320 rows per model), yet the loader supplies an empty assistant response for all 160 final player entries per model, while the actual final responses are stored separately and almost all nonempty. Released runs also contain four distinct final user prompts where the paper states all agents receive identical ones. A white-box context-length baseline separates the released conditions at run level; substituting the actual final responses leaves the Qwen3-32B length score at 1.0 but lowers GPT-OSS-20B's from 0.9175 to 0.75. The condition label is recoverable from prompt construction alone: system-prompt length is a perfect separator in both models, and colluders' final user prompts embed the private coordination transcript verbatim (40/40 colluder, 0/120 honest). An exploratory role-subset tensor diagnostic finds above-chance colluder-role separation across all four released models (AUROC 0.975-1.000 Stego, 0.788-0.961 Transfer); honest-only intervals are model-dependent, including chance in five of eight model-arms. Whether corrected extraction changes detection performance remains unmeasured.

Reviews

Judging this Sprint?

Review “What the released Stego activations contain: an extraction-boundary audit of NARCBench”

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. This submission establishes strong claims on the paper it treats! Indeed, its findings are threats to the validity of NARCBench's Stego evaluation. It is, however, at the same time, difficult to follow the submission.

    The structure does not establish core claims in a sensible manner. More importantly, many paragraphs themselves are very difficult to comprehend and exhibit the usual properties of AI-generated texts.

Cite this project

@misc{seshadri2026released,
  title = {{What the released Stego activations contain: an extraction-boundary audit of NARCBench}},
  author = {Saman Seshadri},
  year = {2026},
  month = oct,
  note = {Submitted to AI Collusion Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/what-the-released-stego-activations-contain-an-extractionboundary-audit-of-narcbench-1m4k}},
  url = {https://apartresearch.com/sprints/projects/what-the-released-stego-activations-contain-an-extractionboundary-audit-of-narcbench-1m4k}
}

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