Skip to content

Xingshu · Tong

pendinghardrobopaint_xingshu—0m 42sunowned

Agent runs

Each mode of this task runs once per run. Est. cost is tokens at list price (data/prices.yml), never a bill; see the RoboPaint runs for every task of a run.

Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default run

TrialStartedAgent timeModel requestsTokens in / outEst. costGrade
U✓ 1h 59m09-28 15:101h 59m24431.1M / 215k$0.485deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, missing_trajectory 0, n_actions 1821, video_rendered 1
L✗ 52m 46%09-29 18:1152m968.0M / 105k$0.151deterministic 1, grader_error 0, instance_exact 1, n_actions 2718, replay_success 0, video_rendered 1

Task instruction (upstream)

Copy the exemplar character 同 in running script (行书), shown in the picture /app/target.png, onto the main sheet with brush and ink, in at most 4 strokes.

Playback speed

Recorded by us: our reference solution, replayed by the verifier (canvas camera, scene camera, side camera, exact canvas).

What RoboPaint states about this task
Success criteria 1. scored against the picture after the best single shift of the sheet, at most 5 mm along each axis
2. IoU >= 0.80
3. boundary F within 1 mm >= 0.75
4. every region of the exemplar's ink covered >= 0.80
5. stray ink <= 0.04 of its inked area
6. at most 4 strokes (continuous brush contacts)
7. both fresh-process replays of the trajectory meet this and end in the same state
Family xingshu
Difficulty hard
Tier privileged
Continuous Score IoU
Grader Facts character — 同
n_strokes — 5
license — Public domain ({{PD-Art
Scoring s.score() is served by a separate scoring container: it replays the actions the agent executed since its last reset on the graders' copy and returns the metrics, never images or target data
Agent Budget 7200 s of wall clock per mode

From our RoboPaint task definitions.

Tags

Task DomainManipulation

Why this task is interesting

Not yet written.

Capability notes

Not yet written.

Oracle demo review

Not yet reviewed.

Discussion