Skip to content
Apart Research
Apart Research
Contact us
Sprint projectMay 25, 2026York, United Kingdom

CwicSpec

Aditya Thalang · Team CwicSpec

Submitted to The Secure Program Synthesis Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: CwicSpec

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

We built a prototype that conjectures candidate specifications for C functions by generating inputs, observing outputs with KLEE, and searching for equivalences between expressions. Inspired by QuickSpec, the project explores whether theory exploration can be applied to C programs. Our implementation is limited by insufficient search-space pruning.

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. Thank you for this work!

    So much software running today is still based on C –in a Mythos world is has become increasingly important that SWE task e.g. to fix up zero-day problems can be addressed swiftly and thoroughly. I'd recommend adding your project's relevance to wider AI safety to strengthen your framing.

    The methods and findings section are very compact: I'd recommend expanding them with more key insights on e.g. the development process, insights the example functions you ran and results overview, etc.

    Honest limitations section.

  2. This project has a clear vision and correctly identifies a high-value target in this space. Applying theory exploration to C is an ambitious choice but unfortunately the scope seems too large to make reasonable progress over the course of a hackathon. A much narrower approach focused on MVP / quick wins would have helped with faster understanding and iteration on tractable parts of the problem-space.

    The authors presented their claims and process candidly and concisely. A ~null result is useful content to produce and may guide future exploration of the domain. However, the results were extremely sparse, making it difficult to understand progress made in this hackathon. I would have liked to see motivating examples which might show promise, or even rough-and-ready analysis of scaling and traits of success/failure attempts.

Cite this project

@misc{thalang2026cwicspec,
  title = {{CwicSpec}},
  author = {Aditya Thalang},
  year = {2026},
  month = may,
  note = {Submitted to The Secure Program Synthesis Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/cwicspec-jzep}},
  url = {https://apartresearch.com/sprints/projects/cwicspec-jzep}
}

More from The Secure Program Synthesis Hackathon

All 61 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026