Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/6f4073b8-d8ea-4ade-8a18-c5d1d5d5aa9a.json

110 lines
2.7 KiB
JSON

{
"id": "6f4073b8-d8ea-4ade-8a18-c5d1d5d5aa9a",
"snapshot": "multiapps",
"instruction": "I now want to count the meeting cities of the three machine learning conferences in the past ten years from 2013 to 2019(including 2013 and 2019). I have listed the names and years of the conferences in excel. Please fill in the vacant locations.",
"source": "author",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/6f4073b8-d8ea-4ade-8a18-c5d1d5d5aa9a/Conference.xlsx",
"path": "/home/user/Desktop/ConferenceCity.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/ConferenceCity.xlsx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"calc",
"chrome",
"os"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/6f4073b8-d8ea-4ade-8a18-c5d1d5d5aa9a/ConferenceCity%20Gold.xlsx",
"path": "/home/user/Desktop/ConferenceCity_Gold.xlsx"
}
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "ConferenceCity.xlsx - LibreOffice Calc"
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey(\"ctrl\", \"s\"); time.sleep(0.5);"
]
}
}
],
"func": "compare_conference_city_in_order",
"expected": {
"type": "rule",
"rules": {
"expected": [
"Scottsdale",
"Atlanta",
"Lake Tahoe",
"Banff",
"Beijing",
[
"Montreal",
"Montréal"
],
"San Diego",
"Lille",
[
"Montreal",
"Montréal"
],
"San Juan",
[
"New York",
"New York City",
"NYC"
],
"Barcelona",
"Toulon",
"Sydney",
"Long Beach",
"Vancouver",
"Stockholm",
[
"Montreal",
"Montréal"
],
"New Orleans",
"Long Beach",
"Vancouver"
]
}
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/ConferenceCity.xlsx",
"dest": "ConferenceCity.xlsx"
}
},
"proxy": false
}