Files
sci-gui-agent-benchmark/evaluation_examples/examples/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json
Danyang Zhang d4273d992e Calc eval fix (#225)
* ver Jun17th

updating annotations

* ver Jun17th

corrected annotation of 1d17
added check for cell merge

* ver Jun17th

updated several annotations

* ver Jun20th

fixed set-up config of 2bd59342-0664-4ccb-ba87-79379096cc08

* fix: Enhance instructions in LibreOffice Calc examples for clarity and specificity, including details on using Pivot Tables, column placements, and revenue calculations.

* ver Jun21st

updating calc evals

* ver Jun22nd

fixed an impress task

* ver Jun22ndv2

adjusted several calc tasks

* Clean scalfolds

---------

Co-authored-by: BowenBryanWang <bryanwang.nlp@connect.hku.hk>
Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-06-30 18:23:09 +08:00

111 lines
2.9 KiB
JSON

{
"id": "ecb0df7a-4e8d-4a03-b162-053391d3afaf",
"snapshot": "libreoffice_calc",
"instruction": "In the column \"Pass/Fail/Held\", one from the texts \"Pass\", \"Fail\", and \"Held\" should be filled. For convinience, enable data validation for the cells in this column so that the texts to fill can be directly selected from a drop down list.",
"source": "https://www.youtube.com/shorts/tXOovKn0H68",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf/Order_Id_Mark_Pass_Fail.xlsx",
"path": "/home/user/Order_Id_Mark_Pass_Fail.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Order_Id_Mark_Pass_Fail.xlsx"
}
}
],
"trajectory": "trajectories/ecb0df7a-4e8d-4a03-b162-053391d3afaf",
"related_apps": [
"libreoffice calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Order_Id_Mark_Pass_Fail.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "data_validation",
"sheet_idx": 0,
"dv_props": [
{
"ranges": {
"method": "spreadsheet_range",
"ref": [
"D2:D29",
"D2:D1048576"
]
},
"type": {
"method": "eq",
"ref": "list"
},
"formula1": {
"method": "str_set_eq",
"ref": [
"Pass",
"Fail",
"Held"
]
}
}
]
}
]
},
"result": {
"type": "vm_file",
"path": "/home/user/Order_Id_Mark_Pass_Fail.xlsx",
"dest": "Order_Id_Mark_Pass_Fail.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf/Order_Id_Mark_Pass_Fail_gold.xlsx",
"dest": "Order_Id_Mark_Pass_Fail_gold.xlsx"
}
},
"proxy": false
}