Kaishu · Shui¶
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
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✓ 1h 44m | 09-28 15:18 | 1h 44m | 196 | 28.4M / 124k | $0.375 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, missing_trajectory 0, n_actions 1716, video_rendered 1 |
| L✗ 31m 61% | 09-29 16:21 | 31m | 70 | 5.7M / 92k | $0.120 | deterministic 1, grader_error 0, instance_exact 1, n_actions 2924, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Copy the exemplar character 水 in regular script (楷书), 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 stroke of the exemplar covered >= 0.80 5. stray ink <= 0.04 of its inked area 6. at most 4 strokes 7. both fresh-process replays of the trajectory meet this and end in the same state |
| Family | kaishu |
| Difficulty | medium |
| Tier | privileged |
| Continuous Score | IoU |
| Grader Facts | character — 水 n_strokes — 4 source — Make Me a Hanzi graphics.txt @ bddc96d (AR PL KaitiM GB / AR PL UKai) license — Arphic Public License tol_mm — 1.0 area_mm2 — 3014.4 |
| 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.