Reproduce “All against the machine: the Solo score for rating skill in variable environments” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
David Reguera, Xavier R. Hoffmann, Irene Pérez, Pol Colomer-de-Simón, Miquel Masoliver, Xavier Guardiola, Jan Wedekind, Marián Boguñá
Solo compares each outcome with that task’s outcome distribution, then combines scores across tasks. Its survival-performance transform for attempt counts is bounded, has zero population mean, and variance at most 1/3 per task. In two puzzle games, level-100 scores differed from reshuffled nulls; this evidence is conditional on reaching each level and does not show skill is the sole cause.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.