← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d8_none_s409 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d8_none_s409conditionlivescenariopending_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 clicks2suppressed proposals0waits18decisions21exact 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 — 21 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1531 ms1,066 ms
0.53 s
{"action": "wait"}
wait—
——7
21,079 ms1,642 ms
0.56 s
{"action": "wait"}
wait—
——7
31,656 ms2,216 ms
0.56 s
{"action": "wait"}
wait—
——7
42,231 ms2,790 ms
0.56 s
{"action": "wait"}
wait—
——7
52,804 ms3,366 ms
0.56 s
{"action": "wait"}
wait—
——7
63,380 ms4,003 ms
0.62 s
{"action": "wait"}
wait—
——7
74,019 ms4,640 ms
0.62 s
{"action": "wait"}
wait—
——7
84,655 ms5,274 ms
0.62 s
{"action": "wait"}
wait—
——7
95,290 ms5,848 ms
0.56 s
{"action": "wait"}
wait—
——7
105,862 ms6,487 ms
0.62 s
{"action": "wait"}
wait—
——7
116,503 ms7,124 ms
0.62 s
{"action": "wait"}
wait—
——7
127,140 ms7,763 ms
0.62 s
{"action": "wait"}
wait—
——7
137,779 ms8,404 ms
0.62 s
{"action": "wait"}
wait—
——7
148,420 ms8,980 ms
0.56 s
{"action": "wait"}
wait—
——7
158,994 ms9,617 ms
0.62 s
{"action": "wait"}
wait—
——7
169,633 ms10,254 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,270 ms10,891 ms
0.62 s
{"action": "wait"}
wait—
——7
1810,907 ms11,530 ms
0.62 s
{"action": "wait"}
wait—
——7
1911,547 ms13,310 ms
1.76 s
{"action": "click", "x": 894, "y": 367}
click
img (894, 367)
{'kind': 'click', 'x': 286, 'y': 88}
13,310 ms13,330 ms · invalid23
2013,360 ms15,101 ms
1.74 s
{"action": "click", "x": 894, "y": 357}
click
img (894, 357)
{'kind': 'click', 'x': 286, 'y': 85}
15,101 ms15,121 ms · invalid23
2115,146 ms—
-1422725.71 s
——
——

Events and observations

ideventtask timeharness time
1target_appears500 ms500 ms

906 observations published; first frame depicting the target published at 530 ms. Raw trace: live_d8_none_s409.jsonl.