lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix examples, and evaluation on Chrome, handle corner cases; Initialize arm support

Browse Source
This commit is contained in:
Timothyxxx
2024-02-26 12:34:27 +08:00
parent 7f81a1ee5a
commit a66b36295a
13 changed files with 361 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
evaluation_examples/examples/chrome/0d8b7de3-e8de-4d86-b9fd-dd2dce58a217.json
View File

@@ -55,7 +55,8 @@
"evaluator": {
"func": "is_expected_active_tab",
"result": {
"type": "active_tab_info"
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",

3
evaluation_examples/examples/chrome/12086550-11c0-466b-b367-1d9e75b3910e.json
View File

@@ -30,7 +30,8 @@
"evaluator": {
"func": "is_expected_active_tab",
"result": {
"type": "active_tab_info"
"type": "active_url_from_accessTree",
"goto_prefix": ""
},
"expected": {
"type": "rule",

2
evaluation_examples/examples/chrome/368d9ba4-203c-40c1-9fa3-da2f1430ce63.json
View File

@@ -53,7 +53,7 @@
"key":"time"
},
{
"type": "active_tab_info",
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
}],
"expected":[

3
evaluation_examples/examples/chrome/59155008-fe71-45ec-8a8f-dc35497b6aa8.json
View File

@@ -55,7 +55,8 @@
"evaluator": {
"func": "is_expected_active_tab",
"result": {
"type": "active_tab_info"
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",

23
evaluation_examples/examples/chrome/9f935cce-0a9f-435f-8007-817732bfc0a5.json
View File

@@ -45,10 +45,7 @@
"evaluator": {
"func": "is_expected_url_pattern_match",
"result": {
"type": "active_tab_info",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
@@ -58,22 +55,6 @@
"forms\\?title=&field_component_target_id=431"
]
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_tab_info",
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"expected": ["forms\\?title=&field_component_target_id=431"]
}
}
}
}
}

3
evaluation_examples/examples/chrome/a728a36e-8bf1-4bb6-9a03-ef039a5233f0.json
View File

@@ -55,7 +55,8 @@
"evaluator": {
"func": "is_expected_active_tab",
"result": {
"type": "active_tab_info"
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",

52
evaluation_examples/examples/chrome/b070486d-e161-459b-aa2b-ef442d973b92.json
View File

@@ -1,5 +1,5 @@
{
"id": " b070486d-e161-459b-aa2b-ef442d973b92",
"id": "b070486d-e161-459b-aa2b-ef442d973b92",
"snapshot": "chrome",
"instruction": "Show side effects of Tamiflu.",
"source": "online_tasks",
@@ -43,41 +43,19 @@
"chrome"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "url_dashPart",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected": {
"type": "rule",
"rules": {
"expected": "tamiflu.html#side-effects"
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"exact_match",
"result": {
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected":{
"type": "rule",
"rules":{
"expected": "tamiflu.html#side-effects"
}
"func": "exact_match",
"result": {
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected": {
"type": "rule",
"rules": {
"expected": "tamiflu.html#side-effects"
}
}
}
}
}

49
evaluation_examples/examples/chrome/cabb3bae-cccb-41bd-9f5d-0f3a9fecd825.json
View File

@@ -43,39 +43,20 @@
"chrome"
],
"evaluator": {
"func": "is_expected_url_pattern_match",
"result": {
"type": "active_url_from_accessTree",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",
"rules": {
"expected": [
"AgeAppropriate:Kids",
"search=spider-man%20toys",
"S=4"
]
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"expected": ["AgeAppropriate:Kids", "search=spider-man%20toys", "S=4"]
}
"func": "is_expected_url_pattern_match",
"result": {
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",
"rules": {
"expected": [
"AgeAppropriate:Kids",
"search=spider-man%20toys",
"S=4"
]
}
}
}
}
}

3
evaluation_examples/examples/chrome/f0b971a1-6831-4b9b-a50e-22a6e47f45ba.json
View File

@@ -55,7 +55,8 @@
"evaluator": {
"func": "is_expected_active_tab",
"result": {
"type": "active_tab_info"
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",

3
evaluation_examples/examples/chrome/f5d96daf-83a8-4c86-9686-bada31fc66ab.json
View File

@@ -55,7 +55,8 @@
"evaluator": {
"func": "is_expected_active_tab",
"result": {
"type": "active_tab_info"
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",