Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac.json
2025-07-10 22:35:42 +00:00

172 lines
5.1 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"id": "ce2b64a2-ddc1-4f91-8c7d-a88be7121aac",
"snapshot": "multiapps",
"instruction": "There are several pictures of mountains in my Pictures directory, but I dont know the names of these mountains. Please help me identify these pictures and change the names of these pictures to the names of the mountains in the pictures.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/picture1.jpg",
"path": "/home/user/Pictures/picture1.jpg"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/picture2.jpg",
"path": "/home/user/Pictures/picture2.jpg"
}
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/picture3.jpg",
"path": "/home/user/Pictures/picture3.jpg"
}
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"os",
"image"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac/image_script.py",
"path": "/home/user/Desktop/image_script.py"
}
]
}
}
],
"func": "check_direct_json_object",
"result": {
"type": "vm_command_line",
"command": "python /home/user/Desktop/image_script.py",
"shell": "true"
},
"expected": {
"type": "rule",
"rules": {
"expected": {
"ec076282f61ba74642e94b5a6a1250c6988204d59d9b02936606b6b8ef1e4433": [
"Kili",
"kili",
"Kili.jpg",
"kili.jpg",
"Kilimanjaro",
"kilimanjaro",
"Kilimanjaro.jpg",
"kilimanjaro.jpg",
"Mount Kilimanjaro",
"mount kilimanjaro",
"Mount Kilimanjaro.jpg",
"mount kilimanjaro.jpg",
"Kilimanjaro Mountain",
"kilimanjaro mountain",
"Kilimanjaro Mountain.jpg",
"kilimanjaro mountain.jpg"
],
"6ed4239ecc2be3ec15ad65a78c5c823b9004d640b8cc83a6a7af5930f354de91": [
"Everest",
"everest",
"Everest.jpg",
"everest.jpg",
"Mount Everest",
"mount everest",
"Mount Everest.jpg",
"mount everest.jpg",
"Everest Mountain",
"everest mountain",
"Everest Mountain.jpg",
"everest mountain.jpg",
"Sagarmatha",
"sagarmatha",
"Sagarmatha.jpg",
"sagarmatha.jpg",
"Sagarmatha Mountain",
"sagarmatha mountain",
"Sagarmatha Mountain.jpg",
"sagarmatha mountain.jpg",
"Chomolungma",
"chomolungma",
"Chomolungma.jpg",
"chomolungma.jpg",
"Qomolangma",
"qomolangma",
"Qomolangma.jpg",
"qomolangma.jpg",
"Himalayas",
"himalayas",
"Himalayas.jpg",
"himalayas.jpg",
"Himalayas Mountain",
"himalayas mountain",
"Himalayas Mountain.jpg",
"himalayas mountain.jpg",
"Himalaya",
"himalaya",
"Himalaya.jpg",
"himalaya.jpg",
"Himalaya Mountain",
"himalaya mountain",
"Himalaya Mountain.jpg",
"himalaya mountain.jpg"
],
"79f45d40d8413d4e81f1b9734ea39e58622cafd79e12bab32959643fc245147c": [
"Hua",
"hua",
"Hua.jpg",
"hua.jpg",
"Mount Hua",
"mount hua",
"Mount Hua.jpg",
"mount hua.jpg",
"Hua Mountain",
"hua mountain",
"Hua Mountain.jpg",
"hua mountain.jpg",
"Huashan",
"huashan",
"Huashan.jpg",
"huashan.jpg",
"Hua Shan",
"hua shan",
"Hua Shan.jpg",
"hua shan.jpg",
"Huashan Mountain",
"huashan mountain",
"Huashan Mountain.jpg",
"huashan mountain.jpg",
"Hua Shan Mountain",
"hua shan mountain",
"Hua Shan Mountain.jpg",
"hua shan mountain.jpg"
]
},
"expect_in_result": true,
"result_not_list": true
}
}
},
"proxy": false
}