Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJan 11, 2026Montreal, Canada

Sandbagging Detection via Static Analysis

Samuel Gelineau, Divyansh Goyal · Team Sandbagging Detection via Static Analysis

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

Read the report

Report: Sandbagging Detection via Static Analysis

Open in a new tab (opens in new tab)
Code (opens in new tab)More on gelisam.com (opens in new tab)
Share

Our sandbagging-detection algorithm is mathematically guaranteed to never label a model as honest if it is actually sandbagging.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

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

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety 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 AI safety 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.

  1. This project presents a formal, provably conservative method for detecting sandbagging in neural networks. The combination of static analysis and witness-input search clearly demonstrates honesty or flags potential sandbagging in small, fully-known models, which is impressive for a hackathon project.

    The main limitation is that the approach is currently restricted to toy networks, so it does not yet scale to real LLMs or complex capabilities. Including examples of how the method might approximate larger models or handle partial knowledge would improve practical relevance. Overall, this is a well-executed theoretical contribution with strong potential for future extensions.

Cite this project

@misc{gelineau2026sandbagging,
  title = {{Sandbagging Detection via Static Analysis}},
  author = {Samuel Gelineau and Divyansh Goyal},
  year = {2026},
  month = jan,
  note = {Submitted to AI Manipulation Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/sandbagging-detection-via-static-analysis-87ip}},
  url = {https://apartresearch.com/sprints/projects/sandbagging-detection-via-static-analysis-87ip}
}

More from AI Manipulation Hackathon

All 70 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026