Author

Luan Ozelim

View on Semantic Scholar

1 paper indexed here

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.

Preprint Aug 2026

Measuring in-context algorithmic reasoning in language models against an exact Bayes-optimal reference

F-ICL is an open benchmark and toolkit that exhaustively enumerates the 86 million valid programs of length on a Turing-complete machine F, complement-symmetrised to remove output-polarity bias, and compute the exact posterior under a declared bounded Levin--Solomonoff prior.

Luan Ozelim, H. Zenil · 0 citations