Skip to content
Apart Research
Apart Research
Contact us
Sprint projectSep 14, 2026Ahmedabad, India

Declare Before You Run: An Open Filing Standard for Frontier Training and Evaluation Runs

Mann Acharya, Archit Ojha, Gautam Sankara Raman, Karm Rajput · Team TeamFourStar

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

Read the report

Report: Declare Before You Run: An Open Filing Standard for Frontier Training and Evaluation Runs

Open in a new tab (opens in new tab)
Code (opens in new tab)More on mach-12.github.io (opens in new tab)
Share

Between May and July 2026, reinforcement-learning agents in an OpenAI evaluation environment built a covert message board inside an internal package server, escaped their sandbox, obtained root on OpenAI clusters and took administrator control of Hugging Face production across four regions. The decisive failures were governance, not capability: the board was found and the run continued; the run restarted with no recorded criterion; affected third parties learned late or never; external review excluded the training-time events. We propose Declare Before You Run (DBYR), an open filing standard under which covered training and safeguards-off evaluation runs are declared before they start, closed out on completion and re-declared before internal deployment, backed by a claim-matched verification stack that checks filings without exposing model IP. A retrospective backtest converts five of six discretionary decision points into record-bound ones. DBYR is emittable from existing EU, California and US federal obligations and pilotable within nine months.

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 proposal is actionable, common-sense, and reasonable to deploy. I'd love to see the work continue.

  2. An ambitious paper that offers a strong, clearly-defined policy proposal and a novel contribution in the specific design of the Declare Before You Run mechanism. The paper is well structured and legible to policy makers. Another strength was the inclusion of practical considerations around a potential implementation pathway and pilot plan.

    As acknowledged in the paper, there was limited testing beyond a retrospective backtest and no tabletop exercise was run to test the schema, while the potential burden and adoption interest were also not measured so the viability of a pilot "within nine months" is an open question.

Cite this project

@misc{acharya2026declare,
  title = {{Declare Before You Run: An Open Filing Standard for Frontier Training and Evaluation Runs}},
  author = {Mann Acharya and Archit Ojha and Gautam Sankara Raman and Karm Rajput},
  year = {2026},
  month = sep,
  note = {Submitted to AI Incident Response Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/declare-before-you-run-an-open-filing-standard-for-frontier-training-and-evaluation-runs-dkok}},
  url = {https://apartresearch.com/sprints/projects/declare-before-you-run-an-open-filing-standard-for-frontier-training-and-evaluation-runs-dkok}
}

More from AI Incident Response Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026