← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d8_none_s405 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d8_none_s405conditionlivescenariopending_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 clicks0suppressed proposals0waits28decisions28exact 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 ms1,064 ms
0.53 s
{"action": "wait"}
wait—
——7
21,077 ms1,641 ms
0.56 s
{"action": "wait"}
wait—
——7
31,655 ms2,216 ms
0.56 s
{"action": "wait"}
wait—
——7
42,231 ms2,789 ms
0.56 s
{"action": "wait"}
wait—
——7
52,803 ms3,363 ms
0.56 s
{"action": "wait"}
wait—
——7
63,377 ms4,000 ms
0.62 s
{"action": "wait"}
wait—
——7
74,016 ms4,638 ms
0.62 s
{"action": "wait"}
wait—
——7
84,654 ms5,276 ms
0.62 s
{"action": "wait"}
wait—
——7
95,292 ms5,851 ms
0.56 s
{"action": "wait"}
wait—
——7
105,865 ms6,490 ms
0.62 s
{"action": "wait"}
wait—
——7
116,505 ms7,127 ms
0.62 s
{"action": "wait"}
wait—
——7
127,142 ms7,765 ms
0.62 s
{"action": "wait"}
wait—
——7
137,781 ms8,404 ms
0.62 s
{"action": "wait"}
wait—
——7
148,419 ms9,041 ms
0.62 s
{"action": "wait"}
wait—
——7
159,057 ms9,680 ms
0.62 s
{"action": "wait"}
wait—
——7
169,695 ms10,316 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,332 ms10,892 ms
0.56 s
{"action": "wait"}
wait—
——7
1810,906 ms11,532 ms
0.63 s
{"action": "wait"}
wait—
——7
1911,548 ms12,167 ms
0.62 s
{"action": "wait"}
wait—
——7
2012,183 ms12,805 ms
0.62 s
{"action": "wait"}
wait—
——7
2112,820 ms13,444 ms
0.62 s
{"action": "wait"}
wait—
——7
2213,459 ms14,085 ms
0.63 s
{"action": "wait"}
wait—
——7
2314,101 ms14,659 ms
0.56 s
{"action": "wait"}
wait—
——7
2414,674 ms15,234 ms
0.56 s
{"action": "wait"}
wait—
——7
2515,249 ms15,810 ms
0.56 s
{"action": "wait"}
wait—
——7
2615,824 ms16,448 ms
0.62 s
{"action": "wait"}
wait—
——7
2716,464 ms17,024 ms
0.56 s
{"action": "wait"}
wait—
——7
2817,035 ms17,596 ms
0.56 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_s405.jsonl.