Public coding-agent RL environment
MathCode
Mini 🧮
Repair a certified bisection solver through typed repository tools, public tests, and a terminal reward. This is an expired, visible compatibility task for researchers to inspect and reproduce.
No paid Space compute requiredOne task, real interaction
The public environment includes a workspace, action budget, test budget, state hashes, replayable events, and a visible contract grader.
Explore the public contract
Taskbisect_repair_v1
Assumption-sensitive repair of a certified numerical solver.
Actions8 typed tools
Inspect, edit, test, inspect the diff, and finish.
Reward7 public checks
Semantic correctness, robustness, and integrity.
Click the button to display the sanitized public report.
Boundary: this static Space displays a
public baseline report. It does not execute arbitrary Python or expose
Ulam’s private evaluator, active tasks, or scorer credentials.