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

Initial commit

Browse Source
This commit is contained in:
lizhanyuan
2026-01-12 18:30:12 +08:00
commit 214e15c04c
102 changed files with 27857 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
tasks/peak_search_001/agent_output/peak_result.pid Executable file
View File

@@ -0,0 +1,81 @@
USER: lzy
JADE: Peak Search Report (72 Peaks, Max P/N = 19.3)
DATE: Friday, Jan 09, 2026 06:13p
FILE: [DEMO01.MDI] Demo01: 37-1497 4-733 9-169 18-303 9-77
SCAN: 5.0/70.0/0.02/1(sec), Cu, I(max)=1542, 01/06/26 11:55
PEAK: 19-pts/Parabolic Filter, Threshold=3.0, Cutoff=0.1%, BG=3/1.0, Peak-Top=Summit
NOTE: Intensity = Counts, 2T(0)=0.0(deg), Wavelength to Compute d-Spacing = 1.54056? (Cu/K-alpha1)
2-Theta d(?) BG Height I% Area I% FWHM
10.818 8.1711 34 261 17.2 2666 12.8 0.174
11.680 7.5700 35 365 24.1 3860 18.5 0.180
13.658 6.4779 30 147 9.7 1450 7.0 0.168
14.225 6.2212 30 62 4.1 515 2.5 0.141
16.981 5.2170 23 176 11.6 3106 14.9 0.300
18.082 4.9017 21 864 57.0 9350 44.9 0.184
20.202 4.3919 22 76 5.0 563 2.7 0.126
20.941 4.2386 34 349 23.0 3214 15.4 0.157
21.783 4.0766 18 208 13.7 3141 15.1 0.257
22.980 3.8670 17 92 6.1 1066 5.1 0.197
25.881 3.4397 14 954 62.9 11045 53.0 0.197
26.502 3.3605 11 87 5.7 1571 7.5 0.307
27.442 3.2475 11 88 5.8 1094 5.3 0.211
27.781 3.2087 11 485 32.0 5123 24.6 0.180
28.239 3.1576 16 161 10.6 1759 8.4 0.186
28.646 3.1137 46 232 15.3 2572 12.3 0.188
28.945 3.0822 13 187 12.3 3765 18.1 0.342
29.279 3.0478 13 300 19.8 3643 17.5 0.206
29.680 3.0075 13 148 9.8 1245 6.0 0.143
30.503 2.9282 17 197 13.0 1945 9.3 0.168
31.058 2.8771 21 807 53.2 8420 40.4 0.177
31.959 2.7981 25 1517 100.0 16539 79.4 0.185
32.443 2.7574 26 160 10.5 2768 13.3 0.294
32.903 2.7199 27 532 35.1 5489 26.4 0.175
33.517 2.6714 42 58 3.8 326 1.6 0.096
34.119 2.6257 22 1353 89.2 20828 100.0 0.262
34.382 2.6062 21 642 42.3 13051 62.7 0.346
35.139 2.5518 16 100 6.6 1206 5.8 0.205
35.638 2.5172 13 233 15.4 2864 13.8 0.209
35.920 2.4980 7 62 4.1 860 4.1 0.236
37.360 2.4050 8 454 29.9 6894 33.1 0.258
37.897 2.3722 6 52 3.4 587 2.8 0.192
39.160 2.2985 11 86 5.7 668 3.2 0.132
39.805 2.2627 9 106 7.0 2291 11.0 0.367
40.044 2.2498 11 251 16.5 3307 15.9 0.224
41.101 2.1943 9 122 8.0 971 4.7 0.135
41.778 2.1603 10 217 14.3 3548 17.0 0.278
42.059 2.1465 10 71 4.7 1054 5.1 0.252
43.018 2.1009 14 48 3.2 324 1.6 0.115
43.939 2.0589 13 184 12.1 2794 13.4 0.258
44.596 2.0301 14 69 4.5 911 4.4 0.224
44.817 2.0207 11 65 4.3 1531 7.4 0.400
45.323 1.9993 12 101 6.7 1770 8.5 0.298
45.561 1.9894 14 156 10.3 2329 11.2 0.254
46.818 1.9388 8 666 43.9 10609 50.9 0.271
47.140 1.9263 7 525 34.6 9530 45.8 0.309
48.120 1.8894 7 187 12.3 3398 16.3 0.309
48.419 1.8784 7 145 9.6 1891 9.1 0.222
49.034 1.8563 14 21 1.4 135 0.6 0.109
49.520 1.8392 8 472 31.1 5989 28.8 0.216
50.379 1.8098 37 183 12.1 2056 9.9 0.191
50.819 1.7952 27 433 28.5 4381 21.0 0.172
51.283 1.7800 14 228 15.0 2666 12.8 0.199
51.903 1.7602 10 174 11.5 1818 8.7 0.178
52.999 1.7263 10 176 11.6 3315 15.9 0.320
53.204 1.7202 10 271 17.9 5366 25.8 0.337
53.862 1.7007 6 180 11.9 1897 9.1 0.179
54.379 1.6858 6 265 17.5 2776 13.3 0.178
55.104 1.6653 5 31 2.0 286 1.4 0.157
56.060 1.6391 5 183 12.1 2265 10.9 0.210
56.603 1.6247 6 53 3.5 400 1.9 0.128
57.198 1.6092 5 168 11.1 2365 11.4 0.239
57.541 1.6004 5 60 4.0 807 3.9 0.229
59.537 1.5514 6 96 6.3 1211 5.8 0.214
60.039 1.5397 6 121 8.0 1692 8.1 0.238
61.342 1.5100 6 147 9.7 1653 7.9 0.191
62.543 1.4839 5 138 9.1 1284 6.2 0.158
63.184 1.4704 4 128 8.4 1902 9.1 0.253
64.200 1.4495 6 417 27.5 4693 22.5 0.191
65.199 1.4297 8 171 11.3 1658 8.0 0.165
66.317 1.4083 3 51 3.4 753 3.6 0.251
67.481 1.3868 3 73 4.8 738 3.5 0.172

81
tasks/peak_search_001/ground_truth/peak_result.pid Executable file
View File

@@ -0,0 +1,81 @@
USER: lzy
JADE: Peak Search Report (72 Peaks, Max P/N = 19.3)
DATE: Friday, Jan 09, 2026 06:13p
FILE: [DEMO01.MDI] Demo01: 37-1497 4-733 9-169 18-303 9-77
SCAN: 5.0/70.0/0.02/1(sec), Cu, I(max)=1542, 01/06/26 11:55
PEAK: 19-pts/Parabolic Filter, Threshold=3.0, Cutoff=0.1%, BG=3/1.0, Peak-Top=Summit
NOTE: Intensity = Counts, 2T(0)=0.0(deg), Wavelength to Compute d-Spacing = 1.54056? (Cu/K-alpha1)
2-Theta d(?) BG Height I% Area I% FWHM
10.818 8.1711 34 261 17.2 2666 12.8 0.174
11.680 7.5700 35 365 24.1 3860 18.5 0.180
13.658 6.4779 30 147 9.7 1450 7.0 0.168
14.225 6.2212 30 62 4.1 515 2.5 0.141
16.981 5.2170 23 176 11.6 3106 14.9 0.300
18.082 4.9017 21 864 57.0 9350 44.9 0.184
20.202 4.3919 22 76 5.0 563 2.7 0.126
20.941 4.2386 34 349 23.0 3214 15.4 0.157
21.783 4.0766 18 208 13.7 3141 15.1 0.257
22.980 3.8670 17 92 6.1 1066 5.1 0.197
25.881 3.4397 14 954 62.9 11045 53.0 0.197
26.502 3.3605 11 87 5.7 1571 7.5 0.307
27.442 3.2475 11 88 5.8 1094 5.3 0.211
27.781 3.2087 11 485 32.0 5123 24.6 0.180
28.239 3.1576 16 161 10.6 1759 8.4 0.186
28.646 3.1137 46 232 15.3 2572 12.3 0.188
28.945 3.0822 13 187 12.3 3765 18.1 0.342
29.279 3.0478 13 300 19.8 3643 17.5 0.206
29.680 3.0075 13 148 9.8 1245 6.0 0.143
30.503 2.9282 17 197 13.0 1945 9.3 0.168
31.058 2.8771 21 807 53.2 8420 40.4 0.177
31.959 2.7981 25 1517 100.0 16539 79.4 0.185
32.443 2.7574 26 160 10.5 2768 13.3 0.294
32.903 2.7199 27 532 35.1 5489 26.4 0.175
33.517 2.6714 42 58 3.8 326 1.6 0.096
34.119 2.6257 22 1353 89.2 20828 100.0 0.262
34.382 2.6062 21 642 42.3 13051 62.7 0.346
35.139 2.5518 16 100 6.6 1206 5.8 0.205
35.638 2.5172 13 233 15.4 2864 13.8 0.209
35.920 2.4980 7 62 4.1 860 4.1 0.236
37.360 2.4050 8 454 29.9 6894 33.1 0.258
37.897 2.3722 6 52 3.4 587 2.8 0.192
39.160 2.2985 11 86 5.7 668 3.2 0.132
39.805 2.2627 9 106 7.0 2291 11.0 0.367
40.044 2.2498 11 251 16.5 3307 15.9 0.224
41.101 2.1943 9 122 8.0 971 4.7 0.135
41.778 2.1603 10 217 14.3 3548 17.0 0.278
42.059 2.1465 10 71 4.7 1054 5.1 0.252
43.018 2.1009 14 48 3.2 324 1.6 0.115
43.939 2.0589 13 184 12.1 2794 13.4 0.258
44.596 2.0301 14 69 4.5 911 4.4 0.224
44.817 2.0207 11 65 4.3 1531 7.4 0.400
45.323 1.9993 12 101 6.7 1770 8.5 0.298
45.561 1.9894 14 156 10.3 2329 11.2 0.254
46.818 1.9388 8 666 43.9 10609 50.9 0.271
47.140 1.9263 7 525 34.6 9530 45.8 0.309
48.120 1.8894 7 187 12.3 3398 16.3 0.309
48.419 1.8784 7 145 9.6 1891 9.1 0.222
49.034 1.8563 14 21 1.4 135 0.6 0.109
49.520 1.8392 8 472 31.1 5989 28.8 0.216
50.379 1.8098 37 183 12.1 2056 9.9 0.191
50.819 1.7952 27 433 28.5 4381 21.0 0.172
51.283 1.7800 14 228 15.0 2666 12.8 0.199
51.903 1.7602 10 174 11.5 1818 8.7 0.178
52.999 1.7263 10 176 11.6 3315 15.9 0.320
53.204 1.7202 10 271 17.9 5366 25.8 0.337
53.862 1.7007 6 180 11.9 1897 9.1 0.179
54.379 1.6858 6 265 17.5 2776 13.3 0.178
55.104 1.6653 5 31 2.0 286 1.4 0.157
56.060 1.6391 5 183 12.1 2265 10.9 0.210
56.603 1.6247 6 53 3.5 400 1.9 0.128
57.198 1.6092 5 168 11.1 2365 11.4 0.239
57.541 1.6004 5 60 4.0 807 3.9 0.229
59.537 1.5514 6 96 6.3 1211 5.8 0.214
60.039 1.5397 6 121 8.0 1692 8.1 0.238
61.342 1.5100 6 147 9.7 1653 7.9 0.191
62.543 1.4839 5 138 9.1 1284 6.2 0.158
63.184 1.4704 4 128 8.4 1902 9.1 0.253
64.200 1.4495 6 417 27.5 4693 22.5 0.191
65.199 1.4297 8 171 11.3 1658 8.0 0.165
66.317 1.4083 3 51 3.4 753 3.6 0.251
67.481 1.3868 3 73 4.8 738 3.5 0.172

260
tasks/peak_search_001/human_demo/actions_raw.json Normal file
View File

@@ -0,0 +1,260 @@
{
"metadata": {
"task_id": "peak_search_001",
"vm_resolution": [
3840,
2160
],
"vm_screenshot_resolution": [
3840,
2160
],
"vm_dpi_scale": 2.0,
"recording_start": "2026-01-09T18:11:24.313862",
"recording_end": "2026-01-09T18:13:29.101588",
"total_duration": 125.18,
"total_actions": 28,
"total_screenshots": 13
},
"actions": [
{
"t": 5.001,
"type": "click",
"button": "left",
"pos_host": [
988.23046875,
844.78125
],
"pos_vm": [
1068,
0
],
"screenshot": "screens/0002_click.png"
},
{
"t": 17.488,
"type": "click",
"button": "left",
"pos_host": [
45.9453125,
326.41015625
],
"pos_vm": [
90,
652
],
"screenshot": "screens/0003_click.png"
},
{
"t": 21.219,
"type": "click",
"button": "left",
"pos_host": [
45.9453125,
326.41015625
],
"pos_vm": [
116,
638
],
"screenshot": "screens/0004_click.png"
},
{
"t": 41.908,
"type": "click",
"button": "right",
"pos_host": [
408.328125,
222.5390625
],
"pos_vm": [
816,
444
],
"screenshot": "screens/0005_click.png"
},
{
"t": 44.055,
"type": "click",
"button": "right",
"pos_host": [
408.328125,
222.5390625
],
"pos_vm": [
816,
444
],
"screenshot": "screens/0006_click.png"
},
{
"t": 54.528,
"type": "click",
"button": "left",
"pos_host": [
778.3359375,
474.0625
],
"pos_vm": [
1556,
948
],
"screenshot": "screens/0007_click.png"
},
{
"t": 74.428,
"type": "click",
"button": "left",
"pos_host": [
710.08984375,
306.734375
],
"pos_vm": [
1420,
612
],
"screenshot": "screens/0008_click.png"
},
{
"t": 94.527,
"type": "click",
"button": "left",
"pos_host": [
545.95703125,
296.1875
],
"pos_vm": [
1090,
592
],
"screenshot": "screens/0009_click.png"
},
{
"t": 101.846,
"type": "key",
"key": "p"
},
{
"t": 102.392,
"type": "key",
"key": "e"
},
{
"t": 102.806,
"type": "key",
"key": "a"
},
{
"t": 102.97,
"type": "key",
"key": "k"
},
{
"t": 103.142,
"type": "key",
"key": "shift"
},
{
"t": 105.349,
"type": "key",
"key": "shift"
},
{
"t": 105.565,
"type": "key",
"key": "_"
},
{
"t": 105.973,
"type": "key",
"key": "r"
},
{
"t": 106.008,
"type": "key",
"key": "e"
},
{
"t": 106.94,
"type": "key",
"key": "s"
},
{
"t": 107.379,
"type": "key",
"key": "u"
},
{
"t": 108.244,
"type": "key",
"key": "l"
},
{
"t": 109.085,
"type": "key",
"key": "t"
},
{
"t": 111.731,
"type": "click",
"button": "left",
"pos_host": [
505.21484375,
451.53125
],
"pos_vm": [
1010,
902
],
"screenshot": "screens/0010_click.png"
},
{
"t": 114.606,
"type": "click",
"button": "left",
"pos_host": [
1204.72265625,
754.12890625
],
"pos_vm": [
2408,
1508
],
"screenshot": "screens/0011_click.png"
},
{
"t": 121.298,
"type": "key",
"key": "ctrl"
},
{
"t": 121.435,
"type": "key",
"key": "left"
},
{
"t": 123.008,
"type": "key",
"key": "ctrl"
},
{
"t": 123.088,
"type": "key",
"key": "c"
},
{
"t": 122.76,
"type": "click",
"button": "left",
"pos_host": [
1007.21875,
1010.23046875
],
"pos_vm": [
1440,
890
],
"screenshot": "screens/0012_click.png"
}
]
}

BIN
tasks/peak_search_001/human_demo/screens/0001_initial.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 15 MiB

BIN
tasks/peak_search_001/human_demo/screens/0002_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 15 MiB

BIN
tasks/peak_search_001/human_demo/screens/0003_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 15 MiB

BIN
tasks/peak_search_001/human_demo/screens/0004_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.6 MiB

BIN
tasks/peak_search_001/human_demo/screens/0005_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.6 MiB

BIN
tasks/peak_search_001/human_demo/screens/0006_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.6 MiB

BIN
tasks/peak_search_001/human_demo/screens/0007_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.6 MiB

BIN
tasks/peak_search_001/human_demo/screens/0008_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.7 MiB

BIN
tasks/peak_search_001/human_demo/screens/0009_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.7 MiB

BIN
tasks/peak_search_001/human_demo/screens/0010_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.7 MiB

BIN
tasks/peak_search_001/human_demo/screens/0011_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.7 MiB

BIN
tasks/peak_search_001/human_demo/screens/0012_click.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.7 MiB

BIN
tasks/peak_search_001/human_demo/screens/0013_final.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.7 MiB

22
tasks/peak_search_001/task.json Normal file
View File

@@ -0,0 +1,22 @@
{
"id": "peak_search_001",
"category": "basic_processing",
"difficulty": "medium",
"instruction": "请打开桌面上的 DEMO01.MDI 文件，进行自动寻峰操作 (Peak Search)，然后,导出峰报告文件并命名为 peak_result.pid。",
"input": {
"source_file": "../../data/source/DEMO01.MDI",
"inject_to": "C:\\Users\\lzy\\Desktop\\DEMO01.MDI"
},
"output": {
"expected_file": "peak_result.pid",
"collect_from": "C:\\Users\\lzy\\Desktop\\peak_result.pid"
},
"evaluation": {
"method": "peak_report_compare",
"ground_truth": "ground_truth/peak_result.pid",
"target_output": "agent_output/peak_result.pid",
"tolerance": 0.01
},
"tutorial_source": "教程(1) - 寻峰部分",
"notes": "自动寻峰并导出峰报告，使用默认寻峰参数"
}