Skip to main content
Try JUWEL

Research / Papers / Sound Compounding Ratchet

Paper · Checking results · Paper

Sound Compounding Ratchet

A way to keep a gain only when a checker confirms it. Plus a test for when a model thinks it passed but did not. Every win here is on tiny models only.

Annalea Layton · Vext Labs · 2026-06-29 · 8 pp · ≈8 min read

  • PROVEN-toy
  • not real-LLM scale
  • $0-CPU kill-tests
Cover · A pixel pattern made from this paper’s ID, “sound-compounding-ratchet” · Art, not a chart
On this page · 1 section
  1. Summary

Summary

A way to keep a gain only when a checker confirms it. Plus a test for when a model thinks it passed but did not. Every win here is on tiny models only.

Read the full paper with the DOI link above.

Authors

Annalea Layton · Vext Labs, Inc. · ORCID 0009-0001-3695-9569

Acknowledgments

None stated in the source paper.

Cite

Layton, A. (2026). Sound Compounding Ratchet. Vext Labs. https://doi.org/10.5281/zenodo.21628552

DOI 10.5281/zenodo.21628552 CC-BY-4.0

Related

  1. 01

    Paper · 2026-07-02 · ≈25 min read

    Beyond the Scaling Ceiling

    A study of how an AI model could grow new skills in checked steps. Every result says how far it goes: tiny model, working code, or waiting on big chips.

    • workshop draft
    • PROVEN-toy
    Read the paper

  2. 02

    Paper · 2026-07-02 · ≈17 min read

    The Accretion Model

    A kind of AI model that grows by adding new parts, never by changing old ones. A stranger can check its whole history. We built a tiny version, Cultivar-0, on a regular computer.

    • BUILT/VERIFIED-CPU
    • PROVEN-toy
    Read the paper

  3. 03

    Paper · 2026-06-27 · ≈10 min read

    The Leakage Signature

    A record of ideas we proved wrong. Plus a way to grow a model that a math solver checks, with an audit for leaks. Small, limited demos only.

    • reproducible artifact
    • no frontier parity claim
    Read the paper
ShareX LinkedIn