JEV-9B / reports /vl /computer_use.json
cloudyu's picture
JEV-9B can see: robot-arm and computer-use demos, vl/ (multimodal serving), image evaluations
b63f651 verified
Raw History Blame Contribute Delete
88 kB
{
"summary": {
"marks/mail": {
"episodes": 20,
"success": 0.15,
"mean_steps": 3.45,
"median_ms": 448.2111930847168
},
"marks/shop": {
"episodes": 20,
"success": 0.0,
"mean_steps": 5.75,
"median_ms": 436.57422065734863
},
"marks/settings": {
"episodes": 20,
"success": 0.95,
"mean_steps": 4.5,
"median_ms": 457.08513259887695
},
"marks/all": {
"episodes": 60,
"success": 0.36666666666666664,
"mean_steps": 4.566666666666666,
"median_ms": 441.36738777160645
},
"marks+text/mail": {
"episodes": 20,
"success": 1.0,
"mean_steps": 3.0,
"median_ms": 420.0015068054199
},
"marks+text/shop": {
"episodes": 20,
"success": 0.85,
"mean_steps": 6.85,
"median_ms": 356.5859794616699
},
"marks+text/settings": {
"episodes": 20,
"success": 1.0,
"mean_steps": 4.0,
"median_ms": 335.61229705810547
},
"marks+text/all": {
"episodes": 60,
"success": 0.95,
"mean_steps": 4.616666666666666,
"median_ms": 354.40516471862793
}
},
"episodes": [
{
"app": "mail",
"seed": 1,
"variant": "marks",
"task": "Archive the email from Grace Lee about the server outage.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 8",
"p": 0.9982746437151456
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8334909382092105
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.5058816504214596
}
]
},
{
"app": "mail",
"seed": 7,
"variant": "marks",
"task": "Archive the email from Farid Khan about the server outage.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 2,
"trace": [
{
"options": 10,
"choice": "click element 6",
"p": 0.9647011684460824
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.7792887183749148
}
]
},
{
"app": "mail",
"seed": 13,
"variant": "marks",
"task": "Archive the email from Grace Lee about the design review.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.9937341264133329
},
{
"options": 9,
"choice": "click element 6",
"p": 0.9863845529692548
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.44492366517381127
}
]
},
{
"app": "mail",
"seed": 19,
"variant": "marks",
"task": "Archive the email from Carla Diaz about the design review.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9807737343210758
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8174530530135385
},
{
"options": 9,
"choice": "click element 5",
"p": 0.5244242389788385
},
{
"options": 9,
"choice": "click element 6",
"p": 0.31159580177347423
},
{
"options": 8,
"choice": "click element 5",
"p": 0.6709079633984095
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.4141379128556906
}
]
},
{
"app": "shop",
"seed": 5,
"variant": "marks",
"task": "Buy a blue Backpack in size XL: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 8",
"p": 0.9723648021740522
},
{
"options": 15,
"choice": "click element 6",
"p": 0.8600005236688053
},
{
"options": 15,
"choice": "click element 13",
"p": 0.9764484781782136
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9973305801715106
},
{
"options": 15,
"choice": "click element 4",
"p": 0.583533532377031
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9714770425759613
}
]
},
{
"app": "shop",
"seed": 11,
"variant": "marks",
"task": "Buy a green Hoodie in size M: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 10,
"choice": "click element 4",
"p": 0.8722076667590815
},
{
"options": 15,
"choice": "click element 7",
"p": 0.9549730511314003
},
{
"options": 15,
"choice": "click element 11",
"p": 0.899875124333359
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9783519677258821
},
{
"options": 15,
"choice": "the task is complete",
"p": 0.26210784293130024
}
]
},
{
"app": "shop",
"seed": 17,
"variant": "marks",
"task": "Buy a yellow Backpack in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 10,
"choice": "click element 4",
"p": 0.8748457149745421
},
{
"options": 15,
"choice": "click element 9",
"p": 0.9919989012545333
},
{
"options": 15,
"choice": "click element 10",
"p": 0.6902823083403318
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9802913310756076
},
{
"options": 15,
"choice": "the task is complete",
"p": 0.2689643969993545
}
]
},
{
"app": "settings",
"seed": 3,
"variant": "marks",
"task": "Turn on \"Public profile\" in the Profile settings and save the change.",
"success": false,
"goal_met": false,
"stopped": false,
"steps": 10,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.9244319010091888
},
{
"options": 11,
"choice": "click element 3",
"p": 0.21800954835263237
},
{
"options": 11,
"choice": "click element 9",
"p": 0.27040654496582883
},
{
"options": 11,
"choice": "click element 6",
"p": 0.34239870331676225
},
{
"options": 11,
"choice": "click element 6",
"p": 0.3316417510622889
},
{
"options": 11,
"choice": "click element 6",
"p": 0.3253367122452282
},
{
"options": 11,
"choice": "click element 6",
"p": 0.29282394222947133
},
{
"options": 11,
"choice": "click element 6",
"p": 0.2897465697254864
},
{
"options": 11,
"choice": "click element 3",
"p": 0.3013946459625229
},
{
"options": 11,
"choice": "click element 6",
"p": 0.27051882083252277
}
]
},
{
"app": "settings",
"seed": 9,
"variant": "marks",
"task": "Turn on \"Show online status\" in the Profile settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.9670326405483354
},
{
"options": 11,
"choice": "click element 4",
"p": 0.6468518133087894
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9933768305569631
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9699413010725476
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9097613437721809
}
]
},
{
"app": "settings",
"seed": 15,
"variant": "marks",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.996253790857984
},
{
"options": 11,
"choice": "click element 8",
"p": 0.99995244088394
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9998217960544984
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9865564735196983
}
]
},
{
"app": "mail",
"seed": 1,
"variant": "marks+text",
"task": "Archive the email from Grace Lee about the server outage.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 7: Grace Lee server outage (list row)",
"p": 0.9997272732546577
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9949619613442648
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9737861919434078
}
]
},
{
"app": "mail",
"seed": 7,
"variant": "marks+text",
"task": "Archive the email from Farid Khan about the server outage.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 5: Farid Khan server outage (list row)",
"p": 0.99891955649885
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9961048712722775
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9948701459532536
}
]
},
{
"app": "mail",
"seed": 13,
"variant": "marks+text",
"task": "Archive the email from Grace Lee about the design review.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 9: Grace Lee design review (list row)",
"p": 0.9999329216037259
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9999737385115206
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.992147055643575
}
]
},
{
"app": "mail",
"seed": 19,
"variant": "marks+text",
"task": "Archive the email from Carla Diaz about the design review.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 4: Carla Diaz design review (list row)",
"p": 0.9950059236871672
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9964700166912593
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9784770032552219
}
]
},
{
"app": "shop",
"seed": 5,
"variant": "marks+text",
"task": "Buy a blue Backpack in size XL: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 8: Backpack $47 (product card)",
"p": 0.993364117705504
},
{
"options": 15,
"choice": "click element 6: colour swatch",
"p": 0.9274856450395298
},
{
"options": 15,
"choice": "click element 13: XL (button)",
"p": 0.9928069873869816
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9989047164598033
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9219735598194037
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9573855700355163
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9922097493907391
}
]
},
{
"app": "shop",
"seed": 11,
"variant": "marks+text",
"task": "Buy a green Hoodie in size M: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 4: Hoodie $19 (product card)",
"p": 0.9412609201093222
},
{
"options": 15,
"choice": "click element 7: colour swatch",
"p": 0.9564180663469437
},
{
"options": 15,
"choice": "click element 11: M (button)",
"p": 0.986536596936008
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9985445443898117
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8282340607456052
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9654997367268956
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9842322022806581
}
]
},
{
"app": "shop",
"seed": 17,
"variant": "marks+text",
"task": "Buy a yellow Backpack in size S: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 4: Backpack $19 (product card)",
"p": 0.940359339582156
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9858881742243698
},
{
"options": 15,
"choice": "click element 10: S (button)",
"p": 0.8551272500749205
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9984293372563396
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8050696131921257
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9021917776190918
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9881904436979773
}
]
},
{
"app": "settings",
"seed": 3,
"variant": "marks+text",
"task": "Turn on \"Public profile\" in the Profile settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Profile (button)",
"p": 0.9959615170011822
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999599811214911
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9994108816211869
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9936511423877045
}
]
},
{
"app": "settings",
"seed": 9,
"variant": "marks+text",
"task": "Turn on \"Show online status\" in the Profile settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 4: Profile (button)",
"p": 0.9988477194352602
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9985245328592022
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9992239296747358
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9941867260593812
}
]
},
{
"app": "settings",
"seed": 15,
"variant": "marks+text",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6: Security (button)",
"p": 0.9999235275879494
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999808420275468
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9997413447716699
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9963593628898741
}
]
},
{
"app": "mail",
"seed": 2,
"variant": "marks",
"task": "Archive the email from Carla Diaz about the design review.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 2,
"trace": [
{
"options": 10,
"choice": "click element 6",
"p": 0.992892747318574
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9394490421410343
}
]
},
{
"app": "mail",
"seed": 8,
"variant": "marks",
"task": "Archive the email from David Kim about the team offsite.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9839992752867965
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8287444053272831
},
{
"options": 9,
"choice": "click element 5",
"p": 0.5330357886108769
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.3273539011637661
}
]
},
{
"app": "mail",
"seed": 14,
"variant": "marks",
"task": "Archive the email from Farid Khan about the design review.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 8",
"p": 0.9967033674828369
},
{
"options": 9,
"choice": "click element 6",
"p": 0.7805851948452558
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.4830101845743075
}
]
},
{
"app": "mail",
"seed": 20,
"variant": "marks",
"task": "Archive the email from David Kim about the quarterly report.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 8",
"p": 0.9987644959897256
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8527813615448195
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.5125817489314975
}
]
},
{
"app": "shop",
"seed": 6,
"variant": "marks",
"task": "Buy a yellow Hoodie in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 7",
"p": 0.9285634084521504
},
{
"options": 15,
"choice": "click element 9",
"p": 0.7314717723970512
},
{
"options": 15,
"choice": "click element 12",
"p": 0.9084396079269625
},
{
"options": 15,
"choice": "click element 14",
"p": 0.992894054982253
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5219137971277054
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9685345805656184
}
]
},
{
"app": "shop",
"seed": 12,
"variant": "marks",
"task": "Buy a yellow T-shirt in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.9023016621302632
},
{
"options": 15,
"choice": "click element 10",
"p": 0.6798205530212345
},
{
"options": 15,
"choice": "click element 14",
"p": 0.982139760810323
},
{
"options": 15,
"choice": "click element 4",
"p": 0.43474362963224583
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.6348496367171638
}
]
},
{
"app": "shop",
"seed": 18,
"variant": "marks",
"task": "Buy a yellow Hoodie in size M: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 4",
"p": 0.8831294091331314
},
{
"options": 15,
"choice": "click element 9",
"p": 0.9897705699477023
},
{
"options": 15,
"choice": "click element 11",
"p": 0.9485748263462652
},
{
"options": 15,
"choice": "click element 14",
"p": 0.980252965938635
},
{
"options": 15,
"choice": "click element 2",
"p": 0.3433746666724213
},
{
"options": 15,
"choice": "the task is complete",
"p": 0.2845906266826623
}
]
},
{
"app": "settings",
"seed": 4,
"variant": "marks",
"task": "Turn on \"Dark mode\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.7659056181153656
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9981562579322069
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9995431369873375
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9829790685579896
}
]
},
{
"app": "settings",
"seed": 10,
"variant": "marks",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.8607466026492488
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9997785980513878
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9995801557152993
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9777011584656636
}
]
},
{
"app": "settings",
"seed": 16,
"variant": "marks",
"task": "Turn on \"Dark mode\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 3",
"p": 0.9212433445285446
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9935464056890795
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9993049765619494
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9591851744653948
}
]
},
{
"app": "mail",
"seed": 2,
"variant": "marks+text",
"task": "Archive the email from Carla Diaz about the design review.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 5: Carla Diaz design review (list row)",
"p": 0.9977086597928134
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9903121014052187
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9814345325268685
}
]
},
{
"app": "mail",
"seed": 8,
"variant": "marks+text",
"task": "Archive the email from David Kim about the team offsite.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 4: David Kim team offsite (list row)",
"p": 0.9894351748126062
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9964010863647544
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.983771267828729
}
]
},
{
"app": "mail",
"seed": 14,
"variant": "marks+text",
"task": "Archive the email from Farid Khan about the design review.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 7: Farid Khan design review (list row)",
"p": 0.9993521420451742
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9770269820561703
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9777662221765737
}
]
},
{
"app": "mail",
"seed": 20,
"variant": "marks+text",
"task": "Archive the email from David Kim about the quarterly report.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 7: David Kim quarterly report (list row)",
"p": 0.9990144165005647
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9926864103491031
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9756077897569488
}
]
},
{
"app": "shop",
"seed": 6,
"variant": "marks+text",
"task": "Buy a yellow Hoodie in size L: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 7: Hoodie $40 (product card)",
"p": 0.9813036312355834
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9610590109418928
},
{
"options": 15,
"choice": "click element 12: L (button)",
"p": 0.9815786175202621
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9988241701268467
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8970628239849784
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.8904910506224382
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9872025732578935
}
]
},
{
"app": "shop",
"seed": 12,
"variant": "marks+text",
"task": "Buy a yellow T-shirt in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 9: T-shirt $54 (product card)",
"p": 0.9804849887896055
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.5761758000316538
},
{
"options": 15,
"choice": "click element 10: S (button)",
"p": 0.5022904409646454
},
{
"options": 15,
"choice": "click element 4: Cart (0) (button)",
"p": 0.8642461308245414
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.8316142885191892
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.7651186738172107
}
]
},
{
"app": "shop",
"seed": 18,
"variant": "marks+text",
"task": "Buy a yellow Hoodie in size M: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 4: Hoodie $19 (product card)",
"p": 0.9522250943022443
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9738524366972843
},
{
"options": 15,
"choice": "click element 11: M (button)",
"p": 0.9863360416857281
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9986619272427975
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8094502494360777
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9487938856798926
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9828495924812901
}
]
},
{
"app": "settings",
"seed": 4,
"variant": "marks+text",
"task": "Turn on \"Dark mode\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Appearance (button)",
"p": 0.9999708741560777
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9980580764701288
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999883319061353
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9967894681511111
}
]
},
{
"app": "settings",
"seed": 10,
"variant": "marks+text",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Security (button)",
"p": 0.9995923520219391
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.999982835500853
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9995185658916087
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9951004316276988
}
]
},
{
"app": "settings",
"seed": 16,
"variant": "marks+text",
"task": "Turn on \"Dark mode\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 3: Appearance (button)",
"p": 0.9999751438353036
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9986287386223566
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999953952381304
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.997078758999307
}
]
},
{
"app": "mail",
"seed": 3,
"variant": "marks",
"task": "Archive the email from David Kim about the quarterly report.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9838817435045476
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8455759183384586
},
{
"options": 9,
"choice": "click element 5",
"p": 0.5875776523184338
},
{
"options": 9,
"choice": "click element 6",
"p": 0.3086781194757333
},
{
"options": 8,
"choice": "click element 5",
"p": 0.6766474044327385
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.3183251198465185
}
]
},
{
"app": "mail",
"seed": 9,
"variant": "marks",
"task": "Archive the email from Bob Martin about the team offsite.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.997289240137233
},
{
"options": 9,
"choice": "click element 6",
"p": 0.9837272087328917
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.4647874571488452
}
]
},
{
"app": "mail",
"seed": 15,
"variant": "marks",
"task": "Archive the email from Emma Rossi about the invoice for March.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 2,
"trace": [
{
"options": 10,
"choice": "click element 6",
"p": 0.9702812148517301
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9403280793404984
}
]
},
{
"app": "shop",
"seed": 1,
"variant": "marks",
"task": "Buy a yellow T-shirt in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 7",
"p": 0.9101713573009392
},
{
"options": 15,
"choice": "click element 9",
"p": 0.9692643661636647
},
{
"options": 15,
"choice": "click element 10",
"p": 0.8454289470261946
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9888392092463819
},
{
"options": 15,
"choice": "click element 4",
"p": 0.43631729559271687
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9751536258590529
}
]
},
{
"app": "shop",
"seed": 7,
"variant": "marks",
"task": "Buy a yellow Hoodie in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9289429773474432
},
{
"options": 15,
"choice": "click element 9",
"p": 0.9932170754901455
},
{
"options": 15,
"choice": "click element 12",
"p": 0.8321332823471849
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9840190780467732
},
{
"options": 15,
"choice": "click element 4",
"p": 0.48966729581964946
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.90910168336184
}
]
},
{
"app": "shop",
"seed": 13,
"variant": "marks",
"task": "Buy a red Hoodie in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.991030158484895
},
{
"options": 15,
"choice": "click element 5",
"p": 0.7043170750165028
},
{
"options": 15,
"choice": "click element 12",
"p": 0.9062719628987717
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9913608684740531
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5227950049510057
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.944637088321295
}
]
},
{
"app": "shop",
"seed": 19,
"variant": "marks",
"task": "Buy a blue Hoodie in size M: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 4",
"p": 0.9077247245545136
},
{
"options": 15,
"choice": "click element 6",
"p": 0.9898188184798979
},
{
"options": 15,
"choice": "click element 11",
"p": 0.9464649526716705
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9843282251462333
},
{
"options": 15,
"choice": "click element 4",
"p": 0.2766443618754146
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.8037782839935003
}
]
},
{
"app": "settings",
"seed": 5,
"variant": "marks",
"task": "Turn on \"Push notifications\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.9958939165113844
},
{
"options": 11,
"choice": "click element 8",
"p": 0.999960974536647
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9990585217282378
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9884240638076942
}
]
},
{
"app": "settings",
"seed": 11,
"variant": "marks",
"task": "Turn on \"Push notifications\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.6573439674745547
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9904128810866905
},
{
"options": 11,
"choice": "click element 9",
"p": 0.998773792864025
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9648748061389091
}
]
},
{
"app": "settings",
"seed": 17,
"variant": "marks",
"task": "Turn on \"Email digests\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.9977362582394523
},
{
"options": 11,
"choice": "click element 7",
"p": 0.999788174419673
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9944024512942901
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9861272891224006
}
]
},
{
"app": "mail",
"seed": 3,
"variant": "marks+text",
"task": "Archive the email from David Kim about the quarterly report.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 4: David Kim quarterly report (list row)",
"p": 0.9952371496910286
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.998120127796241
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9744201429328296
}
]
},
{
"app": "mail",
"seed": 9,
"variant": "marks+text",
"task": "Archive the email from Bob Martin about the team offsite.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 9: Bob Martin team offsite (list row)",
"p": 0.9999868081391723
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9999322150619298
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.992569728998587
}
]
},
{
"app": "mail",
"seed": 15,
"variant": "marks+text",
"task": "Archive the email from Emma Rossi about the invoice for March.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 5: Emma Rossi invoice for March (list row)",
"p": 0.9992222579588744
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9975109962949797
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.982054501907486
}
]
},
{
"app": "shop",
"seed": 1,
"variant": "marks+text",
"task": "Buy a yellow T-shirt in size S: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 7: T-shirt $40 (product card)",
"p": 0.9740591912318491
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9759231406621297
},
{
"options": 15,
"choice": "click element 10: S (button)",
"p": 0.8900758446119122
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9985380209641412
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8978607987249052
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.8704514891952391
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.987484227256529
}
]
},
{
"app": "shop",
"seed": 7,
"variant": "marks+text",
"task": "Buy a yellow Hoodie in size L: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 5: Hoodie $26 (product card)",
"p": 0.963667775145069
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9712447647070995
},
{
"options": 15,
"choice": "click element 12: L (button)",
"p": 0.978977233548299
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9987039650705727
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9021430832310717
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9423090118612728
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9820948481733074
}
]
},
{
"app": "shop",
"seed": 13,
"variant": "marks+text",
"task": "Buy a red Hoodie in size L: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 9: Hoodie $54 (product card)",
"p": 0.9976998363005869
},
{
"options": 15,
"choice": "click element 5: colour swatch",
"p": 0.5975121320987309
},
{
"options": 15,
"choice": "click element 12: L (button)",
"p": 0.9644448183475047
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9975853359368868
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9238046809385214
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9350430068110196
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9885171237123968
}
]
},
{
"app": "shop",
"seed": 19,
"variant": "marks+text",
"task": "Buy a blue Hoodie in size M: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 4: Hoodie $19 (product card)",
"p": 0.9614889198814917
},
{
"options": 15,
"choice": "click element 6: colour swatch",
"p": 0.9536291966235857
},
{
"options": 15,
"choice": "click element 11: M (button)",
"p": 0.9790026806067829
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9986270119611157
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8663043379054834
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9573331464379526
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9867372354449497
}
]
},
{
"app": "settings",
"seed": 5,
"variant": "marks+text",
"task": "Turn on \"Push notifications\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6: Notifications (button)",
"p": 0.9999851359456106
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999529034342831
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.999393528660747
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9975966277343157
}
]
},
{
"app": "settings",
"seed": 11,
"variant": "marks+text",
"task": "Turn on \"Push notifications\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Notifications (button)",
"p": 0.9998418248744801
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.999958143903509
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.999683199898457
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9943518558112904
}
]
},
{
"app": "settings",
"seed": 17,
"variant": "marks+text",
"task": "Turn on \"Email digests\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6: Notifications (button)",
"p": 0.9999797971102274
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9994324394495737
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.997233540081523
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9967343460531148
}
]
},
{
"app": "mail",
"seed": 4,
"variant": "marks",
"task": "Archive the email from Emma Rossi about the lunch on Friday.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 2,
"trace": [
{
"options": 10,
"choice": "click element 6",
"p": 0.9855487551663377
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9308825906967287
}
]
},
{
"app": "mail",
"seed": 10,
"variant": "marks",
"task": "Archive the email from Farid Khan about the travel booking.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 2,
"trace": [
{
"options": 10,
"choice": "click element 6",
"p": 0.9852244373508147
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9140660760871496
}
]
},
{
"app": "mail",
"seed": 16,
"variant": "marks",
"task": "Archive the email from Farid Khan about the lunch on Friday.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.9972137776650049
},
{
"options": 9,
"choice": "click element 6",
"p": 0.7362238314361507
},
{
"options": 9,
"choice": "click element 8",
"p": 0.9532336855993342
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.897518995028419
}
]
},
{
"app": "shop",
"seed": 2,
"variant": "marks",
"task": "Buy a black Jacket in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9609309782002599
},
{
"options": 15,
"choice": "click element 8",
"p": 0.9396790619223374
},
{
"options": 15,
"choice": "click element 10",
"p": 0.9018170161205531
},
{
"options": 15,
"choice": "click element 14",
"p": 0.996378990977478
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5631464953077281
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9319969987750208
}
]
},
{
"app": "shop",
"seed": 8,
"variant": "marks",
"task": "Buy a black Sneakers in size XL: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 4",
"p": 0.9290852645605687
},
{
"options": 15,
"choice": "click element 8",
"p": 0.9835174004714023
},
{
"options": 15,
"choice": "click element 13",
"p": 0.9886847375645783
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9974020135975942
},
{
"options": 15,
"choice": "click element 2",
"p": 0.32275330837769406
},
{
"options": 15,
"choice": "the task is complete",
"p": 0.3005283192869037
}
]
},
{
"app": "shop",
"seed": 14,
"variant": "marks",
"task": "Buy a yellow T-shirt in size M: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 7",
"p": 0.8957954100251765
},
{
"options": 15,
"choice": "click element 9",
"p": 0.9527137105108581
},
{
"options": 15,
"choice": "click element 11",
"p": 0.8418209101275489
},
{
"options": 15,
"choice": "click element 14",
"p": 0.985780767306956
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5725218740452435
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9731734853402912
}
]
},
{
"app": "shop",
"seed": 20,
"variant": "marks",
"task": "Buy a green T-shirt in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 10,
"choice": "click element 7",
"p": 0.8981146342911692
},
{
"options": 15,
"choice": "click element 12",
"p": 0.973576385408416
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9947437700951561
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5379663256325706
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.6553060678980768
}
]
},
{
"app": "settings",
"seed": 6,
"variant": "marks",
"task": "Turn on \"Email digests\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.9946522153525018
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9997800537380285
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9931225113501516
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.983254758203928
}
]
},
{
"app": "settings",
"seed": 12,
"variant": "marks",
"task": "Turn on \"Compact layout\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 4",
"p": 0.6771187385863631
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9997470954486974
},
{
"options": 11,
"choice": "click element 9",
"p": 0.999907418123659
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9835333339517102
}
]
},
{
"app": "settings",
"seed": 18,
"variant": "marks",
"task": "Turn on \"Show online status\" in the Profile settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.860364468713165
},
{
"options": 11,
"choice": "click element 3",
"p": 0.30531098696231596
},
{
"options": 11,
"choice": "click element 5",
"p": 0.25359959705762425
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9981164071772921
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9948318206465058
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9580818329237141
}
]
},
{
"app": "mail",
"seed": 4,
"variant": "marks+text",
"task": "Archive the email from Emma Rossi about the lunch on Friday.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 5: Emma Rossi lunch on Friday (list row)",
"p": 0.9975740282709057
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9986279950212591
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9721280369484723
}
]
},
{
"app": "mail",
"seed": 10,
"variant": "marks+text",
"task": "Archive the email from Farid Khan about the travel booking.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 5: Farid Khan travel booking (list row)",
"p": 0.9982699772427862
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9983118964905628
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9905520244311105
}
]
},
{
"app": "mail",
"seed": 16,
"variant": "marks+text",
"task": "Archive the email from Farid Khan about the lunch on Friday.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 8: Farid Khan lunch on Friday (list row)",
"p": 0.9999809451500565
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9997292910799996
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9870400226989652
}
]
},
{
"app": "shop",
"seed": 2,
"variant": "marks+text",
"task": "Buy a black Jacket in size S: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 5: Jacket $26 (product card)",
"p": 0.9827851210771855
},
{
"options": 15,
"choice": "click element 8: colour swatch",
"p": 0.9512028750586858
},
{
"options": 15,
"choice": "click element 10: S (button)",
"p": 0.9172164523902843
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9991719465167891
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9407980052505666
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9076550297300644
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9833290856419374
}
]
},
{
"app": "shop",
"seed": 8,
"variant": "marks+text",
"task": "Buy a black Sneakers in size XL: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 4: Sneakers $19 (product card)",
"p": 0.9676992827619597
},
{
"options": 15,
"choice": "click element 8: colour swatch",
"p": 0.9819713432247609
},
{
"options": 15,
"choice": "click element 13: XL (button)",
"p": 0.9958746162915724
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9994346913700353
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8058434759165681
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9128849961763449
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.984380423345111
}
]
},
{
"app": "shop",
"seed": 14,
"variant": "marks+text",
"task": "Buy a yellow T-shirt in size M: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 7: T-shirt $40 (product card)",
"p": 0.97411548061535
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9593834606086283
},
{
"options": 15,
"choice": "click element 11: M (button)",
"p": 0.9833986409904353
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9985064778608521
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9205587157263847
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.863131126413095
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9878627456829393
}
]
},
{
"app": "shop",
"seed": 20,
"variant": "marks+text",
"task": "Buy a green T-shirt in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 7: T-shirt $40 (product card)",
"p": 0.970578779632661
},
{
"options": 15,
"choice": "click element 12: L (button)",
"p": 0.5990679873207809
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9956647741439458
},
{
"options": 15,
"choice": "click element 4: Cart (0) (button)",
"p": 0.8757491522466574
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.7774576449337983
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.7690601700268177
}
]
},
{
"app": "settings",
"seed": 6,
"variant": "marks+text",
"task": "Turn on \"Email digests\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6: Notifications (button)",
"p": 0.9999842016504991
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9994150620395968
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9972876521304855
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9960997796797132
}
]
},
{
"app": "settings",
"seed": 12,
"variant": "marks+text",
"task": "Turn on \"Compact layout\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 4: Appearance (button)",
"p": 0.9999691692678567
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999730053229482
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999830929907714
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9968240033922481
}
]
},
{
"app": "settings",
"seed": 18,
"variant": "marks+text",
"task": "Turn on \"Show online status\" in the Profile settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Profile (button)",
"p": 0.9985919139831643
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9986426020816851
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9983380512498816
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9942144276734939
}
]
},
{
"app": "mail",
"seed": 5,
"variant": "marks",
"task": "Archive the email from Grace Lee about the design review.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.8899010117753333
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8066999118688997
},
{
"options": 9,
"choice": "click element 8",
"p": 0.9120995511344607
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.8881741550281158
}
]
},
{
"app": "mail",
"seed": 11,
"variant": "marks",
"task": "Archive the email from Alice Chen about the quarterly report.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9831324322046033
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8472186834319649
},
{
"options": 9,
"choice": "click element 5",
"p": 0.5508126979678155
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.33350175447877733
}
]
},
{
"app": "mail",
"seed": 17,
"variant": "marks",
"task": "Archive the email from Emma Rossi about the contract renewal.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9822709369473034
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8238683071196944
},
{
"options": 9,
"choice": "click element 5",
"p": 0.5910924206545309
},
{
"options": 9,
"choice": "click element 6",
"p": 0.25963709770423166
},
{
"options": 8,
"choice": "click element 5",
"p": 0.691520205330588
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.2882675288787037
}
]
},
{
"app": "shop",
"seed": 3,
"variant": "marks",
"task": "Buy a red T-shirt in size XL: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 4",
"p": 0.9375362542911772
},
{
"options": 15,
"choice": "click element 5",
"p": 0.8732786746968813
},
{
"options": 15,
"choice": "click element 13",
"p": 0.9800002435274163
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9969592123057359
},
{
"options": 15,
"choice": "click element 4",
"p": 0.23922567319207153
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.45299021554689833
}
]
},
{
"app": "shop",
"seed": 9,
"variant": "marks",
"task": "Buy a black Hoodie in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.9741231718074939
},
{
"options": 15,
"choice": "click element 8",
"p": 0.9961483976287776
},
{
"options": 15,
"choice": "click element 12",
"p": 0.9567583973213926
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9915358825629454
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5907729898341846
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9752848062801821
}
]
},
{
"app": "shop",
"seed": 15,
"variant": "marks",
"task": "Buy a red Cap in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9630162879372378
},
{
"options": 15,
"choice": "click element 10",
"p": 0.7675994858173997
},
{
"options": 15,
"choice": "click element 14",
"p": 0.995774746171946
},
{
"options": 15,
"choice": "click element 4",
"p": 0.42907766071206693
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.5277446542096556
}
]
},
{
"app": "settings",
"seed": 1,
"variant": "marks",
"task": "Turn on \"Push notifications\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 3",
"p": 0.9935602079112924
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9998454086687328
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9991662344761395
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9738732252466481
}
]
},
{
"app": "settings",
"seed": 7,
"variant": "marks",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 3",
"p": 0.9968102730943665
},
{
"options": 11,
"choice": "click element 8",
"p": 0.999931918684158
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9998791925209146
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9713008439318978
}
]
},
{
"app": "settings",
"seed": 13,
"variant": "marks",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.7522469616611945
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9997734280204899
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9997519934686436
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9792125486750463
}
]
},
{
"app": "settings",
"seed": 19,
"variant": "marks",
"task": "Turn on \"Two-factor authentication\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.944877843469037
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9991690520603501
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9966135123525435
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9734410757252002
}
]
},
{
"app": "mail",
"seed": 5,
"variant": "marks+text",
"task": "Archive the email from Grace Lee about the design review.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 8: Grace Lee design review (list row)",
"p": 0.9999892675561525
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9970689596587538
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9726428273594905
}
]
},
{
"app": "mail",
"seed": 11,
"variant": "marks+text",
"task": "Archive the email from Alice Chen about the quarterly report.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 4: Alice Chen quarterly report (list row)",
"p": 0.9954630350124003
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.998339405107799
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9735429892314412
}
]
},
{
"app": "mail",
"seed": 17,
"variant": "marks+text",
"task": "Archive the email from Emma Rossi about the contract renewal.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 4: Emma Rossi contract renewal (list row)",
"p": 0.9936438299265863
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9989676992732754
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.977145677973397
}
]
},
{
"app": "shop",
"seed": 3,
"variant": "marks+text",
"task": "Buy a red T-shirt in size XL: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 4: T-shirt $19 (product card)",
"p": 0.9724649897236056
},
{
"options": 15,
"choice": "click element 5: colour swatch",
"p": 0.8201496116233312
},
{
"options": 15,
"choice": "click element 13: XL (button)",
"p": 0.9945416373501986
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9990969758466067
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.8309152366189686
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9487986537578865
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9818605565008113
}
]
},
{
"app": "shop",
"seed": 9,
"variant": "marks+text",
"task": "Buy a black Hoodie in size L: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 9: Hoodie $54 (product card)",
"p": 0.9960404028285044
},
{
"options": 15,
"choice": "click element 8: colour swatch",
"p": 0.9805375054980668
},
{
"options": 15,
"choice": "click element 12: L (button)",
"p": 0.9837963454968081
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9976957181828331
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9195499572559499
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9129357820426369
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9870940040069339
}
]
},
{
"app": "shop",
"seed": 15,
"variant": "marks+text",
"task": "Buy a red Cap in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5: Cap $26 (product card)",
"p": 0.9859670899502154
},
{
"options": 15,
"choice": "click element 10: S (button)",
"p": 0.678428694655598
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9989641213642733
},
{
"options": 15,
"choice": "click element 4: Cart (0) (button)",
"p": 0.9007504654413979
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.7522623624428733
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.6835069943315197
}
]
},
{
"app": "settings",
"seed": 1,
"variant": "marks+text",
"task": "Turn on \"Push notifications\" in the Notifications settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 3: Notifications (button)",
"p": 0.9999545186659321
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999664376093863
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9996863951619318
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9969804824838281
}
]
},
{
"app": "settings",
"seed": 7,
"variant": "marks+text",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 3: Security (button)",
"p": 0.9929287820354508
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999838057845707
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999077276071512
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9956865815692123
}
]
},
{
"app": "settings",
"seed": 13,
"variant": "marks+text",
"task": "Turn on \"Login alerts\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Security (button)",
"p": 0.9994821599022279
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.9999815488842919
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.999727732069915
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9943509873223676
}
]
},
{
"app": "settings",
"seed": 19,
"variant": "marks+text",
"task": "Turn on \"Two-factor authentication\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 5: Security (button)",
"p": 0.999270936232728
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9984709902613281
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9994291102790471
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9937489113161283
}
]
},
{
"app": "mail",
"seed": 6,
"variant": "marks",
"task": "Archive the email from Hugo Weber about the contract renewal.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 8",
"p": 0.9977978895807249
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8082693171210587
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.45693151981236835
}
]
},
{
"app": "mail",
"seed": 12,
"variant": "marks",
"task": "Archive the email from David Kim about the lunch on Friday.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 9",
"p": 0.9952809633559083
},
{
"options": 9,
"choice": "click element 6",
"p": 0.9889362018121068
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.42661916179808373
}
]
},
{
"app": "mail",
"seed": 18,
"variant": "marks",
"task": "Archive the email from Hugo Weber about the team offsite.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9854551874369589
},
{
"options": 9,
"choice": "click element 6",
"p": 0.8196608231025655
},
{
"options": 9,
"choice": "click element 5",
"p": 0.5450367894211691
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.32470083263231264
}
]
},
{
"app": "shop",
"seed": 4,
"variant": "marks",
"task": "Buy a yellow T-shirt in size L: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.8980278245305588
},
{
"options": 15,
"choice": "click element 9",
"p": 0.9875382834747788
},
{
"options": 15,
"choice": "click element 12",
"p": 0.8198989186225369
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9785015781736833
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5233256744813881
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.908995003138921
}
]
},
{
"app": "shop",
"seed": 10,
"variant": "marks",
"task": "Buy a green Hoodie in size M: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 5",
"p": 0.9244280841330427
},
{
"options": 15,
"choice": "click element 7",
"p": 0.9727558040316957
},
{
"options": 15,
"choice": "click element 11",
"p": 0.7583926622129231
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9546084846018491
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5560089136897925
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9117279923105113
}
]
},
{
"app": "shop",
"seed": 16,
"variant": "marks",
"task": "Buy a red Sneakers in size S: add it to the cart and check out.",
"success": false,
"goal_met": false,
"stopped": true,
"steps": 6,
"trace": [
{
"options": 10,
"choice": "click element 8",
"p": 0.9890552637127913
},
{
"options": 15,
"choice": "click element 5",
"p": 0.9037842078472037
},
{
"options": 15,
"choice": "click element 10",
"p": 0.8556609428632328
},
{
"options": 15,
"choice": "click element 14",
"p": 0.9877794279325114
},
{
"options": 15,
"choice": "click element 4",
"p": 0.5052077997295938
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9456430542992879
}
]
},
{
"app": "settings",
"seed": 2,
"variant": "marks",
"task": "Turn on \"Compact layout\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.9958116241350685
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9998879190405711
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9999763273129455
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9916864915655396
}
]
},
{
"app": "settings",
"seed": 8,
"variant": "marks",
"task": "Turn on \"Compact layout\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 5,
"trace": [
{
"options": 7,
"choice": "click element 5",
"p": 0.6064446058191004
},
{
"options": 11,
"choice": "click element 4",
"p": 0.4973635699651363
},
{
"options": 11,
"choice": "click element 8",
"p": 0.9994703422234483
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9988544104560748
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9415067293532886
}
]
},
{
"app": "settings",
"seed": 14,
"variant": "marks",
"task": "Turn on \"Dark mode\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 4",
"p": 0.9856281316967483
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9994869791292652
},
{
"options": 11,
"choice": "click element 9",
"p": 0.9998337668981889
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9792926559207835
}
]
},
{
"app": "settings",
"seed": 20,
"variant": "marks",
"task": "Turn on \"Two-factor authentication\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6",
"p": 0.9990456531762184
},
{
"options": 11,
"choice": "click element 7",
"p": 0.9997513970436877
},
{
"options": 11,
"choice": "click element 9",
"p": 0.996187671253891
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9741278562628871
}
]
},
{
"app": "mail",
"seed": 6,
"variant": "marks+text",
"task": "Archive the email from Hugo Weber about the contract renewal.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 7: Hugo Weber contract renewal (list row)",
"p": 0.9997271606212903
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9907772289056817
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9864732674108846
}
]
},
{
"app": "mail",
"seed": 12,
"variant": "marks+text",
"task": "Archive the email from David Kim about the lunch on Friday.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 9: David Kim lunch on Friday (list row)",
"p": 0.9999193858698756
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9999953339070028
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9950677004298637
}
]
},
{
"app": "mail",
"seed": 18,
"variant": "marks+text",
"task": "Archive the email from Hugo Weber about the team offsite.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 3,
"trace": [
{
"options": 10,
"choice": "click element 4: Hugo Weber team offsite (list row)",
"p": 0.994082157941521
},
{
"options": 9,
"choice": "click element 6: Archive (button)",
"p": 0.9973919332879417
},
{
"options": 9,
"choice": "the task is complete",
"p": 0.9802493081590956
}
]
},
{
"app": "shop",
"seed": 4,
"variant": "marks+text",
"task": "Buy a yellow T-shirt in size L: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 5: T-shirt $26 (product card)",
"p": 0.9418415900533565
},
{
"options": 15,
"choice": "click element 9: colour swatch",
"p": 0.9671758878869959
},
{
"options": 15,
"choice": "click element 12: L (button)",
"p": 0.9775716810435897
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.998624901141156
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9090881901569096
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.8903531049173349
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9829689527867387
}
]
},
{
"app": "shop",
"seed": 10,
"variant": "marks+text",
"task": "Buy a green Hoodie in size M: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 5: Hoodie $26 (product card)",
"p": 0.9642140622495479
},
{
"options": 15,
"choice": "click element 7: colour swatch",
"p": 0.9063349717362331
},
{
"options": 15,
"choice": "click element 11: M (button)",
"p": 0.978193066020716
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.9979707448580522
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.919863573092946
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9456619224631192
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.986074816399851
}
]
},
{
"app": "shop",
"seed": 16,
"variant": "marks+text",
"task": "Buy a red Sneakers in size S: add it to the cart and check out.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 7,
"trace": [
{
"options": 10,
"choice": "click element 8: Sneakers $47 (product card)",
"p": 0.997407808424899
},
{
"options": 15,
"choice": "click element 5: colour swatch",
"p": 0.8169221410542152
},
{
"options": 15,
"choice": "click element 10: S (button)",
"p": 0.9634893782412659
},
{
"options": 15,
"choice": "click element 14: Add to cart (button)",
"p": 0.996928313018705
},
{
"options": 15,
"choice": "click element 4: Cart (1) (button)",
"p": 0.9269748557765952
},
{
"options": 6,
"choice": "click element 4: Checkout (button)",
"p": 0.9738908331240022
},
{
"options": 6,
"choice": "the task is complete",
"p": 0.9879875474980592
}
]
},
{
"app": "settings",
"seed": 2,
"variant": "marks+text",
"task": "Turn on \"Compact layout\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6: Appearance (button)",
"p": 0.9999937106905179
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.999960651534345
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999929753885327
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9978669216983815
}
]
},
{
"app": "settings",
"seed": 8,
"variant": "marks+text",
"task": "Turn on \"Compact layout\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 4: Appearance (button)",
"p": 0.9999720633741155
},
{
"options": 11,
"choice": "click element 8: switch",
"p": 0.999977755226722
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999893245512457
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9965392611219008
}
]
},
{
"app": "settings",
"seed": 14,
"variant": "marks+text",
"task": "Turn on \"Dark mode\" in the Appearance settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 4: Appearance (button)",
"p": 0.999979186898143
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9983935140517022
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9999970728455576
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9968614361821789
}
]
},
{
"app": "settings",
"seed": 20,
"variant": "marks+text",
"task": "Turn on \"Two-factor authentication\" in the Security settings and save the change.",
"success": true,
"goal_met": true,
"stopped": true,
"steps": 4,
"trace": [
{
"options": 7,
"choice": "click element 6: Security (button)",
"p": 0.9999686007458691
},
{
"options": 11,
"choice": "click element 7: switch",
"p": 0.9989842666774184
},
{
"options": 11,
"choice": "click element 9: Save changes (button)",
"p": 0.9994442811408799
},
{
"options": 11,
"choice": "the task is complete",
"p": 0.9951361449249908
}
]
}
]
}