Method

Scalabrino

The comprehensive model of Scalabrino et al. combines structural, textual, and visual features. We call the authors' released Java archive and pretrained classifier through a local adapter, wrapping method snippets in a minimal class where required. The published features and scoring logic are unchanged. Unsupported or failed samples are omitted.

Score scale: 0–1; higher is more readable.

Official tool download · Adapter code and instructions

Dataset results