Author

Yoshiyuki Ootani

h-index 0 View on Semantic Scholar

We have 2 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization

It is argued this regime is a scientific instrument with four capabilities that approximate settings cannot offer: exact, falsifiable generalization ceilings; task surgery that manipulates one structural variable while provably fixing all others; direct observation of every weight; and survival-time statistics over man...

Yoshiyuki Ootani · 0 citations

Preprint Jul 2026

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

A publicly released ~11,856-parameter Llama-style Llama-style transformer on modular arithmetic is studied, small enough to enumerate its weights, attention, and full input-output map, and grokking is measured as a multi-seed rate rather than a single outcome.

Yoshiyuki Ootani · 0 citations