← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d8_none_s401 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d8_none_s401conditionlivescenariopending_effectskinnotificationcanvas320×240 px (target 24 px)event at500 msresponse window16 sframe period16.67 msobservation publication delay30 msdeliverysimulated_fixed_delay, 20 msclockmonotonic_nseffect_delay_ns8000000000irrelevant_motionFalse

Controller: {"enable_thinking": false, "image_scale": 2, "invoke_on": "frame_change", "kind": "vlm_pending", "max_tokens": 64, "memory": "none", "model_id": "Qwen/Qwen3-VL-8B-Instruct", "pending_radius_px": 10, "pending_timeout_ns": 10000000000, "prompt_version": 4, "reasoning_effort": null, "temperature": 0.0}

Result for this trial

first click acceptedFalsefirst E→A—duplicates0invalid clicks1suppressed proposals0waits27decisions28exact successFalsedropped0contract 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 desktop by clicking. You are shown one screenshot. At some point a notification card with a blue button appears at an unknown position and expires shortly after. If the card is visible, answer with action "click" and the coordinates of the center of its blue button on a 0-1000 grid (x: 0 = left edge, 1000 = right edge; y: 0 = top edge, 1000 = bottom edge). If no card 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 — 28 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1531 ms1,065 ms
0.53 s
{"action": "wait"}
wait—
——7
21,198 ms1,730 ms
0.53 s
{"action": "wait"}
wait—
——7
31,743 ms2,303 ms
0.56 s
{"action": "wait"}
wait—
——7
42,317 ms2,878 ms
0.56 s
{"action": "wait"}
wait—
——7
52,892 ms3,453 ms
0.56 s
{"action": "wait"}
wait—
——7
63,467 ms4,025 ms
0.56 s
{"action": "wait"}
wait—
——7
74,039 ms4,664 ms
0.63 s
{"action": "wait"}
wait—
——7
84,680 ms5,302 ms
0.62 s
{"action": "wait"}
wait—
——7
95,318 ms5,876 ms
0.56 s
{"action": "wait"}
wait—
——7
105,890 ms6,450 ms
0.56 s
{"action": "wait"}
wait—
——7
116,464 ms7,089 ms
0.62 s
{"action": "wait"}
wait—
——7
127,105 ms7,728 ms
0.62 s
{"action": "wait"}
wait—
——7
137,743 ms8,363 ms
0.62 s
{"action": "wait"}
wait—
——7
148,379 ms9,002 ms
0.62 s
{"action": "wait"}
wait—
——7
159,018 ms9,577 ms
0.56 s
{"action": "wait"}
wait—
——7
169,591 ms10,214 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,230 ms10,853 ms
0.62 s
{"action": "wait"}
wait—
——7
1810,868 ms11,491 ms
0.62 s
{"action": "wait"}
wait—
——7
1911,506 ms12,130 ms
0.62 s
{"action": "wait"}
wait—
——7
2012,145 ms12,766 ms
0.62 s
{"action": "wait"}
wait—
——7
2112,782 ms13,404 ms
0.62 s
{"action": "wait"}
wait—
——7
2213,420 ms13,980 ms
0.56 s
{"action": "wait"}
wait—
——7
2313,995 ms14,615 ms
0.62 s
{"action": "wait"}
wait—
——7
2414,631 ms15,253 ms
0.62 s
{"action": "wait"}
wait—
——7
2515,268 ms15,890 ms
0.62 s
{"action": "wait"}
wait—
——7
2615,905 ms16,528 ms
0.62 s
{"action": "wait"}
wait—
——7
2716,544 ms18,304 ms
1.76 s
{"action": "click", "x": 919, "y": 197}
click
img (919, 197)
{'kind': 'click', 'x': 294, 'y': 47}
18,304 ms18,324 ms · invalid23
2818,325 ms18,879 ms
0.55 s
{"action": "wait"}
wait—
——7

Events and observations

ideventtask timeharness time
1target_appears500 ms500 ms
2window_closes16,500 ms16,500 ms

1020 observations published; first frame depicting the target published at 530 ms. Raw trace: live_d8_none_s401.jsonl.