chart-elo-ratings
A four-state arena ratings card: one line per model with a confidence band derived from its battle count, releases annotated with the rating move they produced, a standings ladder that flags statistically tied neighbours, and a pairwise win-rate matrix that doubles as the keyboard-navigable control surface.
chart-elo-ratings
A four-state arena ratings card: one line per model with a confidence band derived from its battle count, releases annotated with the rating move they produced, a standings ladder that flags statistically tied neighbours, and a pairwise win-rate matrix that doubles as the keyboard-navigable control surface.