🧠 AI Ed Wiki

Debugging exercises are usually graded from final code and test outcomes, which hide how students reproduced failures, formed hypotheses, inspected evidence, edited code, and verified fixes. The authors present DebugTracker, a Visual Studio Code extension that records lightweight debugging-process evidence for classroom tasks. It separates uncoached Evaluation Mode traces from coached Training Mode traces, stores append-only JSONL events, and exports timeline and Markdown reports for human review, capturing test commands, debugger metadata, student checkpoints, source snapshots, optional image evidence, human labels, and optional AI-assisted practice feedback. The largely language-agnostic prototype was validated across Python, TypeScript, and Java with 16 automated checks and an 11-case manual trial matrix spanning packaged VSIX installation on three operating systems.

  • Process over product: Surfaces the hidden debugging workflow, moving assessment beyond final artifacts toward Formative Assessment of process.
  • Coached vs uncoached modes: Distinguishes Training from Evaluation traces, enabling differentiation of guidance effects in Programming ITS.
  • Lightweight, language-agnostic capture: VS Code-standard mechanisms reduce instructor setup burden, supporting CS Education at scale.
  • AI-assisted practice feedback: Optional automated feedback loops tie into Feedback Loop research.
  • Learning analytics: Append-only event logs feed Learning Analytics on how students debug, informing Student Experience design.
  • Connected Concepts

  • Formative Assessment
  • CS Education
  • Feedback Loop
  • Learning Analytics
  • Student Experience
  • Connected Articles

  • Programming ITS
  • Citation

    Liu, J., Yao, X., Zhang, Z., & Tian, Y. (2026). DebugTracker: Lightweight Process Evidence for Classroom Debugging. arXiv:2607.05871.