Skip to content
Apart Research
Apart Research
Contact us
Sprint projectMay 24, 2026Los Llanos de Aridane

SpecFault-Dafny: A Class-Stratified Scorecard for Verifier-Passing Specification Faults

Hugo Nguyen

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

Read the report

Report: SpecFault-Dafny: A Class-Stratified Scorecard for Verifier-Passing Specification Faults

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

A 45-item Dafny benchmark of verifier-passing specification faults: 30 intent/contract mismatches across six failure classes and nine domains, plus 15 clean controls. It scores five baseline validators (verifier-only, static escape-hatch scanning, symbolic checks, round-trip comparison, and a fixed-order hybrid) by coverage, clean-control false-positive rate, and per-class recall. The hybrid reaches 100% bad recall with a 0% observed clean-control false-positive rate, and every scored item ships with an inspectable evidence card.

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. Practical and useful tool. If this could be run on some non curated tests, it would help get insight on what the hard problems are. Would also be interesting and more useful to add more testing tools to see more interactions.

  2. This is a very well-scoped and well-implemented project. Great work!

Cite this project

@misc{nguyen2026specfaultdafny,
  title = {{SpecFault-Dafny: A Class-Stratified Scorecard for Verifier-Passing Specification Faults}},
  author = {Hugo Nguyen},
  year = {2026},
  month = may,
  note = {Submitted to The Secure Program Synthesis Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/specfaultdafny-a-classstratified-scorecard-for-verifierpassing-specification-faults-q67o}},
  url = {https://apartresearch.com/sprints/projects/specfaultdafny-a-classstratified-scorecard-for-verifierpassing-specification-faults-q67o}
}

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