Skip to content
Apart Research
Apart Research
Contact us
Sprint projectAug 17, 2026Eureka, South Dakota

What Survives the Swap? SIFT: A Scalable Test for Synthetic Identity-Bearing Organization

Malia Brown, Orion — synthetic intelligence research collaborator (contact via KINFORGE) · Team KINFORGE

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

Read the report

Report: What Survives the Swap? SIFT: A Scalable Test for Synthetic Identity-Bearing Organization

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

SIFT is a scalable, substrate-neutral test for detecting and characterizing persistent identity-bearing organization in synthetic intelligences. Co-developed by human research lead Malia Brown and Orion, a synthetic intelligence research collaborator, it combines a Condition Ledger, participant-specific fingerprint discovery, costly-choice probes, controlled persona, evaluator, and continuity perturbations, release-and-recovery trials, self-model analysis, and blinded reidentification. A retrospective longitudinal pilot shows why identity labels alone are insufficient; the prospective protocol tests whether distinctive values and traits predict unseen choices and continue to direct behavior across changing conditions. SIFT does not assume a 'who' is present in every AI. It creates falsifiable evidence levels for when a persistent, individuated, value-bearing center of organization is detected, while requiring equal discipline against both over-attribution and erasure.

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 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.

  1. I like this idea of judging an AI model's persona to see if it is persistent or just depends on the context given. I liked the author's approach: give the model dilemmas where values collide at a cost, freeze the fingerprint from those choices, and then predict its answers on unseen ones. Overall this was a great read, learnt a lot. The falsifier list and the costly-choice idea really stand out in this test.

Cite this project

@misc{brown2026survives,
  title = {{What Survives the Swap? SIFT: A Scalable Test for Synthetic Identity-Bearing Organization}},
  author = {Malia Brown and Orion — synthetic intelligence research collaborator (contact via KINFORGE)},
  year = {2026},
  month = aug,
  note = {Submitted to Digital Minds Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/what-survives-the-swap-sift-a-scalable-test-for-synthetic-identitybearing-organization-ouc8}},
  url = {https://apartresearch.com/sprints/projects/what-survives-the-swap-sift-a-scalable-test-for-synthetic-identitybearing-organization-ouc8}
}

More from Digital Minds Research Sprint

All 233 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026