← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d8_none_s402 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d8_none_s402conditionlivescenariopending_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 clicks3suppressed proposals0waits19decisions22exact 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 — 22 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1531 ms1,063 ms
0.53 s
{"action": "wait"}
wait—
——7
21,076 ms1,638 ms
0.56 s
{"action": "wait"}
wait—
——7
31,652 ms2,211 ms
0.56 s
{"action": "wait"}
wait—
——7
42,225 ms2,785 ms
0.56 s
{"action": "wait"}
wait—
——7
52,800 ms3,359 ms
0.56 s
{"action": "wait"}
wait—
——7
63,373 ms3,996 ms
0.62 s
{"action": "wait"}
wait—
——7
74,011 ms4,633 ms
0.62 s
{"action": "wait"}
wait—
——7
84,649 ms5,208 ms
0.56 s
{"action": "wait"}
wait—
——7
95,222 ms5,781 ms
0.56 s
{"action": "wait"}
wait—
——7
105,796 ms6,420 ms
0.62 s
{"action": "wait"}
wait—
——7
116,435 ms7,059 ms
0.62 s
{"action": "wait"}
wait—
——7
127,074 ms7,696 ms
0.62 s
{"action": "wait"}
wait—
——7
137,712 ms8,335 ms
0.62 s
{"action": "wait"}
wait—
——7
148,351 ms8,974 ms
0.62 s
{"action": "wait"}
wait—
——7
158,989 ms9,608 ms
0.62 s
{"action": "wait"}
wait—
——7
169,624 ms10,244 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,259 ms10,884 ms
0.62 s
{"action": "wait"}
wait—
——7
1810,900 ms11,519 ms
0.62 s
{"action": "wait"}
wait—
——7
1911,535 ms13,300 ms
1.76 s
{"action": "click", "x": 901, "y": 187}
click
img (901, 187)
{'kind': 'click', 'x': 288, 'y': 44}
13,300 ms13,320 ms · invalid23
2013,347 ms15,092 ms
1.74 s
{"action": "click", "x": 901, "y": 187}
click
img (901, 187)
{'kind': 'click', 'x': 288, 'y': 44}
15,092 ms15,112 ms · invalid23
2115,135 ms16,881 ms
1.75 s
{"action": "click", "x": 901, "y": 197}
click
img (901, 197)
{'kind': 'click', 'x': 288, 'y': 47}
16,881 ms16,901 ms · invalid23
2216,923 ms17,455 ms
0.53 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_s402.jsonl.