e433f35c1f
- Add `fixed_ip` field to all 369 JSON files in examples directory - Set to `true` for 8 files listed in google_chrome.json multi_apps - Set to `false` for remaining 361 files - Add `possibility_of_env_change` field to 363 JSON files missing this field - Set to "low" for newly added fields - Preserve existing values (4 medium, 2 high) for 6 files that already had this field This ensures consistent configuration schema across all evaluation examples while maintaining backward compatibility with existing settings.
89 lines
2.2 KiB
JSON
89 lines
2.2 KiB
JSON
{
|
|
"id": "aceb0368-56b8-4073-b70e-3dc9aee184e0",
|
|
"snapshot": "libreoffice_calc",
|
|
"instruction": "I am grading students' English exam papers, but the test consists only of multiple-choice questions. It's too exhausting to check each question one by one and record the detailed scores. Can you help me compare the remaining students' answers with the answer key and record the detailed scoring in the opened spreadsheet?",
|
|
"source": "authors",
|
|
"config": [
|
|
{
|
|
"type": "download",
|
|
"parameters": {
|
|
"files": [
|
|
{
|
|
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/aceb0368-56b8-4073-b70e-3dc9aee184e0/exam.zip",
|
|
"path": "/home/user/exam.zip"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "execute",
|
|
"parameters": {
|
|
"command": [
|
|
"unzip",
|
|
"/home/user/exam.zip",
|
|
"-d",
|
|
"/home/user/"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"libreoffice",
|
|
"--writer",
|
|
"/home/user/exam/ReferenceAnswers.docx"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"libreoffice",
|
|
"--calc",
|
|
"/home/user/exam/grades.xlsx"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"nautilus",
|
|
"/home/user/exam/"
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"trajectory": "trajectories/",
|
|
"related_apps": [
|
|
"thunderbird",
|
|
"os"
|
|
],
|
|
"evaluator": {
|
|
"func": "compare_table",
|
|
"expected": {
|
|
"type": "cloud_file",
|
|
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/aceb0368-56b8-4073-b70e-3dc9aee184e0/grades.xlsx",
|
|
"dest": "gold_grades.xlsx"
|
|
},
|
|
"result": {
|
|
"type": "vm_file",
|
|
"path": "/home/user/exam/grades.xlsx",
|
|
"dest": "grades.xlsx"
|
|
},
|
|
"options": {
|
|
"rules": [
|
|
{
|
|
"type": "sheet_data",
|
|
"sheet_idx0": 0,
|
|
"sheet_idx1": "EI0"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"proxy": false,
|
|
"fixed_ip": false,
|
|
"possibility_of_env_change": "low"
|
|
} |