← all runs · ← report

wi004_qwen38_nothink / live_v0_frozen_s300 valid

What this trial was

runwi004_qwen38_nothinktriallive_v0_frozen_s300conditionlivescenariomoving_targetskinballooncanvas320×240 px (target 24 px)event at500 msresponse window16 sframe period16.67 msobservation publication delay30 msdeliverysimulated_fixed_delay, 20 msclockmonotonic_nsvelocity_x_px_per_s0velocity_y_px_per_s0irrelevant_motionFalse

Controller: {"at_commit_policy": "frozen", "enable_thinking": false, "image_scale": 2, "invoke_on": "frame_change", "kind": "vlm_late_binding", "max_tokens": 64, "min_match_score": 0.8, "model_id": "Qwen/Qwen3.8-27B", "prompt_version": 5, "reasoning_effort": null, "restart_threshold_px": null, "temperature": 0.0, "template_radius_px": 12}

Result for this trial

valid at ATruelabels—bindingstate_at_Bspatial error at A2.2 pxfrozen counterfactual at same Arestarts0B→D (committing decision)5.24 sE→O / O→D / D→A / E→A30 ms / 5245 ms / 20 ms / 5295 msdecisions1valid trialTruecontract violationsnone

Replay

animated replay

Recorded frames from the first decision to the last receipt, every 4th frame, time compressed 10×; red = committed click.

key frames

Key frames: each decision's starting frame with the click it produced (amber = proposal before binding, red = committed, grey = suppressed), then the screen at each arrival A (green = valid).

The prompt sent with every frame

You control a game by clicking. You are shown one screenshot. A red balloon appears at an unknown position and may drift; it disappears after a short time. If the balloon is visible, answer with action "click" and the coordinates of the center of the red balloon on a 0-1000 grid (x: 0 = left edge, 1000 = right edge; y: 0 = top edge, 1000 = bottom edge). If no balloon is visible, answer with action "wait". Answer with the JSON object only.

[user] Screenshot attached. Click the target's center or wait.

Decision by decision — 1 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1532 ms5,775 ms
5.24 s
{"action": "click", "x": 615, "y": 423}
click
img (615, 423)
{'kind': 'click', 'x': 196, 'y': 101}
5,775 ms5,795 ms · VALID23

Events and observations

ideventtask timeharness time
1target_appears500 ms500 ms

346 observations published; first frame depicting the target published at 530 ms. Raw trace: live_v0_frozen_s300.jsonl.