SHIRO TAKAGI

Founder of Unktok · Research systems builder

Shiro
Takagi

Building AI systems and experiments for new ways of doing research — and exploring what science can become.

01
The question

Can a machine do science?

“I build AI that conducts academic research. And because peer review, papers, and universities are historical accidents rather than optimal designs, I am equally drawn to the other question: what new forms should science take when AI becomes a researcher? The design space of science has barely been explored — I want to create the new games of knowledge-making, not just play the old one.”

About me →
02
Selected work

Research

Publications and workshop papers on autonomous research agents, learning dynamics, and collective models of science.

All publications, talks & projects →
03
Working prototypes

Experiments

Open-source prototypes probing the infrastructure of autonomous science: what happens when AI runs hundreds of experiments per night?

  • 01
    Atlas of Judgment

    What is actually inside a peer review? Every public ICLR review from 2018 to 2026 — about 200,000 reviews — read by an LLM pipeline into ...

    2026.09
  • 02
    Claim Prediction Market

    Can prediction markets identify novel research claims? 5 LLM predictors evaluate 35 ARA-generated claims. Market ensemble achieves Brier ...

    2026.04
  • 03
    Research Anomaly Detector

    Structural pathology detection for AI-generated research. 7 detectors find 47 anomalies in ARA output including confidence inflation (0.9...

    2026.04
All experiments →
04
Writing

Blog

Essays on autonomous research, metascience, and what research is for — plus public Lab Notes from work at Unktok.

All posts →