{ "summary": { "marks/mail": { "episodes": 20, "success": 0.0, "mean_steps": 3.45, "median_ms": 609.8916530609131 }, "marks/shop": { "episodes": 20, "success": 0.05, "mean_steps": 6.25, "median_ms": 561.9170665740967 }, "marks/settings": { "episodes": 20, "success": 0.4, "mean_steps": 4.9, "median_ms": 492.77353286743164 }, "marks/all": { "episodes": 60, "success": 0.15, "mean_steps": 4.866666666666666, "median_ms": 559.3726634979248 }, "marks+text/mail": { "episodes": 20, "success": 1.0, "mean_steps": 3.0, "median_ms": 426.23162269592285 }, "marks+text/shop": { "episodes": 20, "success": 0.85, "mean_steps": 7.45, "median_ms": 368.0124282836914 }, "marks+text/settings": { "episodes": 20, "success": 1.0, "mean_steps": 4.0, "median_ms": 419.85416412353516 }, "marks+text/all": { "episodes": 60, "success": 0.95, "mean_steps": 4.816666666666666, "median_ms": 394.08421516418457 } }, "seconds": 91.25923871994019, "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": 0.9832235952101744 }, { "options": 9, "choice": "click element 6", "p": 0.9485597613908374 }, { "options": 9, "choice": "the task is complete", "p": 0.5522118909179 } ], "latency_s": [ 10.708057165145874, 0.6098916530609131, 5.5383687019348145 ] }, { "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": 0.9837772809153351 }, { "options": 9, "choice": "the task is complete", "p": 0.9894110963883601 } ], "latency_s": [ 2.419621706008911, 0.5732367038726807 ] }, { "app": "mail", "seed": 13, "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 5", "p": 0.44404231902228775 }, { "options": 9, "choice": "click element 6", "p": 0.9675476215276583 }, { "options": 9, "choice": "click element 8", "p": 0.5762696676611854 }, { "options": 9, "choice": "the task is complete", "p": 0.9649059330433327 } ], "latency_s": [ 2.3871467113494873, 0.5959744453430176, 0.5763959884643555, 0.8019890785217285 ] }, { "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": 4, "trace": [ { "options": 10, "choice": "click element 5", "p": 0.9473434177699953 }, { "options": 9, "choice": "click element 6", "p": 0.9794875544985033 }, { "options": 9, "choice": "click element 5", "p": 0.8085069508919327 }, { "options": 9, "choice": "the task is complete", "p": 0.8525918375699174 } ], "latency_s": [ 0.5505545139312744, 0.5631670951843262, 0.5630989074707031, 0.5878674983978271 ] }, { "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": 0.992952291636174 }, { "options": 15, "choice": "click element 6", "p": 0.8783418553838996 }, { "options": 15, "choice": "click element 13", "p": 0.9781411586573598 }, { "options": 15, "choice": "click element 14", "p": 0.9459586592399682 }, { "options": 15, "choice": "click element 4", "p": 0.9877348991456176 }, { "options": 6, "choice": "the task is complete", "p": 0.76873373898785 } ], "latency_s": [ 0.5211083889007568, 0.5910434722900391, 0.5716404914855957, 0.565847635269165, 0.5906128883361816, 0.6169025897979736 ] }, { "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": 6, "trace": [ { "options": 10, "choice": "click element 4", "p": 0.999110474440147 }, { "options": 15, "choice": "click element 7", "p": 0.8371631602090436 }, { "options": 15, "choice": "click element 11", "p": 0.9597415571295043 }, { "options": 15, "choice": "click element 14", "p": 0.9373586342230016 }, { "options": 15, "choice": "click element 2", "p": 0.5701538616116902 }, { "options": 15, "choice": "the task is complete", "p": 0.752045198968583 } ], "latency_s": [ 0.49535512924194336, 0.5034511089324951, 0.6653647422790527, 0.4960606098175049, 2.954789400100708, 0.6034336090087891 ] }, { "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": 6, "trace": [ { "options": 10, "choice": "click element 4", "p": 0.9991468083959262 }, { "options": 15, "choice": "click element 9", "p": 0.927693619127074 }, { "options": 15, "choice": "click element 10", "p": 0.8949230575997297 }, { "options": 15, "choice": "click element 14", "p": 0.871117227933617 }, { "options": 15, "choice": "click element 4", "p": 0.6193478666386245 }, { "options": 6, "choice": "the task is complete", "p": 0.8414298080648852 } ], "latency_s": [ 0.4739673137664795, 0.541663408279419, 0.5851485729217529, 0.5650808811187744, 0.5391621589660645, 0.5501136779785156 ] }, { "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": true, "steps": 5, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.9980410095195356 }, { "options": 11, "choice": "click element 9", "p": 0.8507836605529168 }, { "options": 11, "choice": "click element 6", "p": 0.6305265194040841 }, { "options": 11, "choice": "click element 9", "p": 0.949273787362328 }, { "options": 11, "choice": "the task is complete", "p": 0.3925074575266011 } ], "latency_s": [ 0.5216710567474365, 0.5556035041809082, 0.5498921871185303, 0.5731163024902344, 0.4800443649291992 ] }, { "app": "settings", "seed": 9, "variant": "marks", "task": "Turn on \"Show online status\" in the Profile settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 3, "trace": [ { "options": 7, "choice": "click element 5", "p": 0.9989477434671097 }, { "options": 11, "choice": "click element 9", "p": 0.8585736158631527 }, { "options": 11, "choice": "the task is complete", "p": 0.3565466764625783 } ], "latency_s": [ 0.36635828018188477, 0.5468695163726807, 0.5505256652832031 ] }, { "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": 5, "trace": [ { "options": 7, "choice": "click element 3", "p": 0.41658785583108743 }, { "options": 11, "choice": "click element 6", "p": 0.9546296513930774 }, { "options": 11, "choice": "click element 8", "p": 0.9641312234866299 }, { "options": 11, "choice": "click element 9", "p": 0.8741118707139531 }, { "options": 11, "choice": "the task is complete", "p": 0.9945813699576298 } ], "latency_s": [ 0.5868749618530273, 0.3195619583129883, 0.4302370548248291, 0.4140603542327881, 0.5214371681213379 ] }, { "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": 0.9988277814291545 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9943721901069814 }, { "options": 9, "choice": "the task is complete", "p": 0.9880632704366256 } ], "latency_s": [ 0.43532276153564453, 0.5066969394683838, 0.5782842636108398 ] }, { "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": 0.9998935329861511 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9994011904447367 }, { "options": 9, "choice": "the task is complete", "p": 0.9808418756716824 } ], "latency_s": [ 0.3979613780975342, 0.37180280685424805, 0.5842587947845459 ] }, { "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": 0.9988293843523623 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9997891734809017 }, { "options": 9, "choice": "the task is complete", "p": 0.9884987035857962 } ], "latency_s": [ 0.3534364700317383, 0.4593989849090576, 0.5512380599975586 ] }, { "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": 0.9987284357163365 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9987830270416097 }, { "options": 9, "choice": "the task is complete", "p": 0.981566107204909 } ], "latency_s": [ 0.3773055076599121, 0.42623162269592285, 0.3934791088104248 ] }, { "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": 0.9998824830839544 }, { "options": 15, "choice": "click element 6: colour swatch", "p": 0.955927757544567 }, { "options": 15, "choice": "click element 13: XL (button)", "p": 0.9690532285975536 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9701489909774114 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9946439730296025 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9980965756999828 }, { "options": 6, "choice": "the task is complete", "p": 0.9492786407258043 } ], "latency_s": [ 0.3299696445465088, 0.40250158309936523, 0.3886430263519287, 0.4300673007965088, 0.5018720626831055, 0.3818807601928711, 2.782362461090088 ] }, { "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": 0.999928709845151 }, { "options": 15, "choice": "click element 7: colour swatch", "p": 0.9642652957491629 }, { "options": 15, "choice": "click element 11: M (button)", "p": 0.9100239574238137 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.953351411470982 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9848370581063639 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9972557509501775 }, { "options": 6, "choice": "the task is complete", "p": 0.9430701972951673 } ], "latency_s": [ 0.27518749237060547, 0.331449031829834, 0.32833099365234375, 0.4266548156738281, 0.347947359085083, 0.38909363746643066, 0.43877267837524414 ] }, { "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": 0.9999366725215396 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.984173936846314 }, { "options": 15, "choice": "click element 10: S (button)", "p": 0.9457556369790953 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9332025539435483 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9845442993753419 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9955150916071408 }, { "options": 6, "choice": "the task is complete", "p": 0.9207229653441609 } ], "latency_s": [ 0.28668785095214844, 0.3455233573913574, 0.46100330352783203, 0.3312337398529053, 0.4646174907684326, 0.3348808288574219, 0.43546533584594727 ] }, { "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": 0.9998966645371128 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9721874507091799 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9926411693358504 }, { "options": 11, "choice": "the task is complete", "p": 0.997944219949445 } ], "latency_s": [ 0.29402947425842285, 0.41594505310058594, 0.40079641342163086, 0.35628271102905273 ] }, { "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": 0.999068857697872 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9877161124566632 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9987339328664453 }, { "options": 11, "choice": "the task is complete", "p": 0.9979821962282074 } ], "latency_s": [ 0.2782320976257324, 0.6423966884613037, 0.5652999877929688, 0.5839323997497559 ] }, { "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": 0.9981035610458234 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9779600842710038 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9873969686048462 }, { "options": 11, "choice": "the task is complete", "p": 0.989960016928268 } ], "latency_s": [ 0.277188777923584, 0.41640233993530273, 0.4898867607116699, 0.5089812278747559 ] }, { "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": 0.9126452316116547 }, { "options": 9, "choice": "the task is complete", "p": 0.994374418796727 } ], "latency_s": [ 10.641320705413818, 0.6102850437164307 ] }, { "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": 0.9385405501663396 }, { "options": 9, "choice": "click element 6", "p": 0.9663318373658892 }, { "options": 9, "choice": "click element 5", "p": 0.5478049721432204 }, { "options": 9, "choice": "the task is complete", "p": 0.5620412207933301 } ], "latency_s": [ 5.45515513420105, 2.5057194232940674, 0.5838263034820557, 2.4392855167388916 ] }, { "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": 0.9828103117406883 }, { "options": 9, "choice": "click element 6", "p": 0.953214160592756 }, { "options": 9, "choice": "the task is complete", "p": 0.564874959460858 } ], "latency_s": [ 0.5307424068450928, 0.569443941116333, 0.8067595958709717 ] }, { "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": 4, "trace": [ { "options": 10, "choice": "click element 8", "p": 0.9736933960130697 }, { "options": 9, "choice": "click element 6", "p": 0.9535350061974094 }, { "options": 9, "choice": "click element 8", "p": 0.5493346212363331 }, { "options": 9, "choice": "the task is complete", "p": 0.6900808334191924 } ], "latency_s": [ 0.5360040664672852, 0.5852386951446533, 0.5544130802154541, 0.587134599685669 ] }, { "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": 0.9978144925406287 }, { "options": 15, "choice": "click element 9", "p": 0.9451833543407013 }, { "options": 15, "choice": "click element 12", "p": 0.941880277059501 }, { "options": 15, "choice": "click element 14", "p": 0.9554368833858565 }, { "options": 15, "choice": "click element 4", "p": 0.9800345796336913 }, { "options": 6, "choice": "the task is complete", "p": 0.6999533614184155 } ], "latency_s": [ 0.49158430099487305, 0.591235876083374, 0.5746057033538818, 0.5750303268432617, 0.5727348327636719, 0.6096029281616211 ] }, { "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": 8, "trace": [ { "options": 10, "choice": "click element 9", "p": 0.9995229956989469 }, { "options": 15, "choice": "click element 10", "p": 0.933623823015292 }, { "options": 15, "choice": "click element 14", "p": 0.9630362431024295 }, { "options": 15, "choice": "click element 4", "p": 0.7591734319679576 }, { "options": 6, "choice": "click element 4", "p": 0.6789923912561913 }, { "options": 6, "choice": "click element 4", "p": 0.5416243682144096 }, { "options": 6, "choice": "click element 4", "p": 0.5455660389586349 }, { "options": 6, "choice": "the task is complete", "p": 0.41487205389577947 } ], "latency_s": [ 0.4845149517059326, 0.5074319839477539, 0.5058281421661377, 0.45654749870300293, 0.4376711845397949, 2.5773324966430664, 0.588951826095581, 0.5475471019744873 ] }, { "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": 0.9992668821315358 }, { "options": 15, "choice": "click element 9", "p": 0.898299394168487 }, { "options": 15, "choice": "click element 11", "p": 0.9699423142653011 }, { "options": 15, "choice": "click element 14", "p": 0.9374981063183009 }, { "options": 15, "choice": "click element 4", "p": 0.4766713853385831 }, { "options": 6, "choice": "the task is complete", "p": 0.7833606677827988 } ], "latency_s": [ 0.48180341720581055, 0.5749313831329346, 0.5681455135345459, 0.5252811908721924, 0.7021856307983398, 0.4473698139190674 ] }, { "app": "settings", "seed": 4, "variant": "marks", "task": "Turn on \"Dark mode\" in the Appearance settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 5, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.9939635287138173 }, { "options": 11, "choice": "click element 9", "p": 0.605082761111144 }, { "options": 11, "choice": "click element 6", "p": 0.4168223312182974 }, { "options": 11, "choice": "click element 9", "p": 0.9890848874199779 }, { "options": 11, "choice": "the task is complete", "p": 0.43637359216692406 } ], "latency_s": [ 0.47694897651672363, 0.5604422092437744, 0.5632493495941162, 0.4791593551635742, 0.4063255786895752 ] }, { "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": 5, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.992335955079473 }, { "options": 11, "choice": "click element 5", "p": 0.608992563663935 }, { "options": 11, "choice": "click element 8", "p": 0.9316857970067387 }, { "options": 11, "choice": "click element 9", "p": 0.9389118494535836 }, { "options": 11, "choice": "the task is complete", "p": 0.9907880906773772 } ], "latency_s": [ 0.5027883052825928, 0.548551082611084, 0.6498994827270508, 0.33476901054382324, 0.42821240425109863 ] }, { "app": "settings", "seed": 16, "variant": "marks", "task": "Turn on \"Dark mode\" in the Appearance settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 6, "trace": [ { "options": 7, "choice": "click element 4", "p": 0.999232102871524 }, { "options": 11, "choice": "click element 9", "p": 0.8989723634136884 }, { "options": 11, "choice": "click element 9", "p": 0.4450114102812057 }, { "options": 11, "choice": "click element 4", "p": 0.7570136562476493 }, { "options": 11, "choice": "click element 9", "p": 0.9756264513090634 }, { "options": 11, "choice": "the task is complete", "p": 0.4259341986345033 } ], "latency_s": [ 0.34412264823913574, 0.5276331901550293, 0.5143835544586182, 0.5141749382019043, 0.5733489990234375, 0.4778931140899658 ] }, { "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": 0.9996678751945388 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9990077882393119 }, { "options": 9, "choice": "the task is complete", "p": 0.9880846162818855 } ], "latency_s": [ 0.29915833473205566, 0.588890790939331, 0.4118812084197998 ] }, { "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": 0.9971081212189843 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.999110310288901 }, { "options": 9, "choice": "the task is complete", "p": 0.9893758511805604 } ], "latency_s": [ 0.40024852752685547, 0.5424811840057373, 0.4413740634918213 ] }, { "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": 0.9993022488278125 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9920097132455363 }, { "options": 9, "choice": "the task is complete", "p": 0.9936162372454056 } ], "latency_s": [ 0.36333584785461426, 0.39171695709228516, 0.39058637619018555 ] }, { "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": 0.9979093846265183 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9993167023496297 }, { "options": 9, "choice": "the task is complete", "p": 0.991680486247545 } ], "latency_s": [ 0.3356294631958008, 0.38565826416015625, 0.47731852531433105 ] }, { "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": 0.9999260033117428 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.9121714932761827 }, { "options": 15, "choice": "click element 12: L (button)", "p": 0.9299714865175474 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9899121916112876 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9901909891037126 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9960303622799734 }, { "options": 6, "choice": "the task is complete", "p": 0.8886270260102146 } ], "latency_s": [ 0.4005775451660156, 0.38010358810424805, 2.7667956352233887, 0.35788464546203613, 0.35043931007385254, 0.3476855754852295, 0.431382417678833 ] }, { "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": false, "steps": 10, "trace": [ { "options": 10, "choice": "click element 9: T-shirt $54 (product card)", "p": 0.9999647342748675 }, { "options": 15, "choice": "click element 10: S (button)", "p": 0.9815931246153021 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.832240525909871 }, { "options": 15, "choice": "click element 4: Cart (0) (button)", "p": 0.9418338145404221 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9319096028596949 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.5971490477832055 }, { "options": 6, "choice": "click element 3: \u2190 Continue shopping (button)", "p": 0.41855154675360573 }, { "options": 10, "choice": "click element 9: T-shirt $54 (product card)", "p": 0.838432938973932 }, { "options": 15, "choice": "click element 4: Cart (0) (button)", "p": 0.32668700736130246 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.8816151187673135 } ], "latency_s": [ 0.2736983299255371, 0.3811159133911133, 0.4163846969604492, 0.3574810028076172, 0.3510279655456543, 0.0738990306854248, 0.2524559497833252, 0.33510398864746094, 0.464587926864624, 0.3483414649963379 ] }, { "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": 0.9998132649841345 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.9880669999486824 }, { "options": 15, "choice": "click element 11: M (button)", "p": 0.9481965223978988 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9413069334391208 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9863406898396525 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9949388079323936 }, { "options": 6, "choice": "the task is complete", "p": 0.9360989632736227 } ], "latency_s": [ 0.32572102546691895, 0.34206604957580566, 0.41641855239868164, 0.4055802822113037, 0.35959887504577637, 0.3551633358001709, 0.4795362949371338 ] }, { "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": 0.9988377592393022 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9862129453111032 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.999666991153774 }, { "options": 11, "choice": "the task is complete", "p": 0.9974862965208702 } ], "latency_s": [ 0.08246183395385742, 0.400890588760376, 0.585989236831665, 0.3364980220794678 ] }, { "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": 0.9991276188038933 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9752116229402097 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9926000193996527 }, { "options": 11, "choice": "the task is complete", "p": 0.9965422645683398 } ], "latency_s": [ 0.36417508125305176, 0.49051547050476074, 0.5003948211669922, 0.46877384185791016 ] }, { "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": 0.9996755395766477 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9857963762554316 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9996456727068934 }, { "options": 11, "choice": "the task is complete", "p": 0.997064359961334 } ], "latency_s": [ 0.4083263874053955, 0.35872483253479004, 0.4746105670928955, 0.45796918869018555 ] }, { "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": 4, "trace": [ { "options": 10, "choice": "click element 5", "p": 0.9672994704892839 }, { "options": 9, "choice": "click element 6", "p": 0.9352221888807142 }, { "options": 9, "choice": "click element 5", "p": 0.8262647645971498 }, { "options": 9, "choice": "the task is complete", "p": 0.6369929297925504 } ], "latency_s": [ 10.638067245483398, 0.6087837219238281, 5.536390781402588, 2.499969482421875 ] }, { "app": "mail", "seed": 9, "variant": "marks", "task": "Archive the email from Bob Martin about the team offsite.", "success": false, "goal_met": false, "stopped": true, "steps": 4, "trace": [ { "options": 10, "choice": "click element 5", "p": 0.4398175057661783 }, { "options": 9, "choice": "click element 6", "p": 0.9783054017067982 }, { "options": 9, "choice": "click element 8", "p": 0.63088619891951 }, { "options": 9, "choice": "the task is complete", "p": 0.9825684139483423 } ], "latency_s": [ 0.5053513050079346, 2.4447426795959473, 0.5812280178070068, 0.5899670124053955 ] }, { "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": 0.9772748523521265 }, { "options": 9, "choice": "the task is complete", "p": 0.9935049922684747 } ], "latency_s": [ 0.7350754737854004, 0.6015374660491943 ] }, { "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": 0.9921420339638277 }, { "options": 15, "choice": "click element 9", "p": 0.9553336257600735 }, { "options": 15, "choice": "click element 10", "p": 0.839758854856203 }, { "options": 15, "choice": "click element 14", "p": 0.8966137246366899 }, { "options": 15, "choice": "click element 4", "p": 0.9674213200950951 }, { "options": 6, "choice": "the task is complete", "p": 0.9066196109390483 } ], "latency_s": [ 0.5432944297790527, 0.5666134357452393, 0.573638916015625, 0.5567460060119629, 0.6060609817504883, 0.5888874530792236 ] }, { "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": 0.9995438707632235 }, { "options": 15, "choice": "click element 9", "p": 0.9905770208667697 }, { "options": 15, "choice": "click element 12", "p": 0.9811033340600478 }, { "options": 15, "choice": "click element 14", "p": 0.9553833205944988 }, { "options": 15, "choice": "click element 4", "p": 0.9717338986955768 }, { "options": 6, "choice": "the task is complete", "p": 0.7244346975190682 } ], "latency_s": [ 0.49782443046569824, 0.5983657836914062, 0.6032934188842773, 0.5595076084136963, 0.5055456161499023, 0.09641385078430176 ] }, { "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": 0.9992475855104264 }, { "options": 15, "choice": "click element 5", "p": 0.6203366803638324 }, { "options": 15, "choice": "click element 12", "p": 0.9664371100804853 }, { "options": 15, "choice": "click element 14", "p": 0.8775275903592809 }, { "options": 15, "choice": "click element 4", "p": 0.9916449005042167 }, { "options": 6, "choice": "the task is complete", "p": 0.7199192522232993 } ], "latency_s": [ 0.32700347900390625, 0.49666285514831543, 2.9880788326263428, 0.5803496837615967, 0.5400576591491699, 0.5377845764160156 ] }, { "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": 0.998960626592514 }, { "options": 15, "choice": "click element 6", "p": 0.9035836960832392 }, { "options": 15, "choice": "click element 11", "p": 0.9656495108358316 }, { "options": 15, "choice": "click element 14", "p": 0.9359955749234142 }, { "options": 15, "choice": "click element 4", "p": 0.6260068398486243 }, { "options": 6, "choice": "the task is complete", "p": 0.6596210766765576 } ], "latency_s": [ 0.5147926807403564, 0.5593726634979248, 0.5177164077758789, 0.7050631046295166, 0.4297020435333252, 0.5256352424621582 ] }, { "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": 5, "trace": [ { "options": 7, "choice": "click element 4", "p": 0.33852563569912425 }, { "options": 11, "choice": "click element 6", "p": 0.9134514538845525 }, { "options": 11, "choice": "click element 8", "p": 0.9547210119889693 }, { "options": 11, "choice": "click element 9", "p": 0.9791281257378173 }, { "options": 11, "choice": "the task is complete", "p": 0.9857672235042981 } ], "latency_s": [ 0.5063326358795166, 0.5393834114074707, 0.47843289375305176, 0.41888976097106934, 0.5624098777770996 ] }, { "app": "settings", "seed": 11, "variant": "marks", "task": "Turn on \"Push notifications\" in the Notifications settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 3, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.9964686376553821 }, { "options": 11, "choice": "click element 9", "p": 0.6423585661715311 }, { "options": 11, "choice": "the task is complete", "p": 0.38605615772533936 } ], "latency_s": [ 0.49301576614379883, 0.4926474094390869, 0.48281359672546387 ] }, { "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": 0.9779855953722084 }, { "options": 11, "choice": "click element 7", "p": 0.9959570404065887 }, { "options": 11, "choice": "click element 9", "p": 0.9953339229421103 }, { "options": 11, "choice": "the task is complete", "p": 0.9976844186636726 } ], "latency_s": [ 0.37026262283325195, 0.4117929935455322, 0.5225601196289062, 0.507713794708252 ] }, { "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": 0.9986193869092737 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9999215365538797 }, { "options": 9, "choice": "the task is complete", "p": 0.9850903555564664 } ], "latency_s": [ 0.43492722511291504, 0.5673816204071045, 0.4790782928466797 ] }, { "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": 0.9995724365084923 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9999002777316095 }, { "options": 9, "choice": "the task is complete", "p": 0.9900164037924353 } ], "latency_s": [ 0.2864968776702881, 0.5886781215667725, 0.42432475090026855 ] }, { "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": 0.9997201716157398 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9996560128980736 }, { "options": 9, "choice": "the task is complete", "p": 0.9762305131283683 } ], "latency_s": [ 0.40233802795410156, 0.5354938507080078, 0.4377307891845703 ] }, { "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": 0.9999031056653676 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.8692706770298269 }, { "options": 15, "choice": "click element 10: S (button)", "p": 0.9517487760477321 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9798292448718248 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9736796904480273 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9942692590815535 }, { "options": 6, "choice": "the task is complete", "p": 0.9363633232291405 } ], "latency_s": [ 0.36887168884277344, 0.3925201892852783, 0.40375232696533203, 0.3968021869659424, 0.3680124282836914, 0.4911980628967285, 0.4951446056365967 ] }, { "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": 0.9999871879318166 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.9851246320033796 }, { "options": 15, "choice": "click element 12: L (button)", "p": 0.9454369542084256 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9738735682117585 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9868555547318001 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9964815685750579 }, { "options": 6, "choice": "the task is complete", "p": 0.9003057386497184 } ], "latency_s": [ 0.3596513271331787, 2.7750906944274902, 0.3545825481414795, 0.35582733154296875, 0.34946155548095703, 0.43152832984924316, 0.3578808307647705 ] }, { "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": 0.999971932352228 }, { "options": 15, "choice": "click element 5: colour swatch", "p": 0.5887661528142384 }, { "options": 15, "choice": "click element 12: L (button)", "p": 0.9155328097364034 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9793904522145452 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9892370291054631 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9964940507699981 }, { "options": 6, "choice": "the task is complete", "p": 0.9429657504907085 } ], "latency_s": [ 0.3165912628173828, 0.40567708015441895, 0.3515477180480957, 0.34485554695129395, 0.4544403553009033, 0.3374443054199219, 0.4597296714782715 ] }, { "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": 0.9996825341343522 }, { "options": 15, "choice": "click element 6: colour swatch", "p": 0.9911511590657271 }, { "options": 15, "choice": "click element 11: M (button)", "p": 0.9357245139048197 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9627376662216007 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9913289171057524 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9975609948370118 }, { "options": 6, "choice": "the task is complete", "p": 0.9494890950813628 } ], "latency_s": [ 0.27001333236694336, 0.41477441787719727, 0.3334319591522217, 0.39408421516418457, 0.38986778259277344, 0.3802933692932129, 0.3417658805847168 ] }, { "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": 0.9995058227148922 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9780686340648028 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9990697019276169 }, { "options": 11, "choice": "the task is complete", "p": 0.9977510867867673 } ], "latency_s": [ 0.5864222049713135, 0.554699182510376, 0.43096041679382324, 0.3152737617492676 ] }, { "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": 0.999813311776763 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9685621672839807 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9934452324992893 }, { "options": 11, "choice": "the task is complete", "p": 0.9975548501289216 } ], "latency_s": [ 0.07142806053161621, 0.2775156497955322, 0.47751665115356445, 0.5165572166442871 ] }, { "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": 0.9992564595580824 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9932587957316843 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9982169967609265 }, { "options": 11, "choice": "the task is complete", "p": 0.9975519379249852 } ], "latency_s": [ 0.42731213569641113, 0.4775841236114502, 0.35687828063964844, 0.48177361488342285 ] }, { "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": 0.9729247231924375 }, { "options": 9, "choice": "the task is complete", "p": 0.9776712032420409 } ], "latency_s": [ 10.64253306388855, 0.6127874851226807 ] }, { "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": 0.9669002583255134 }, { "options": 9, "choice": "the task is complete", "p": 0.9925126420058755 } ], "latency_s": [ 5.450570583343506, 2.5005571842193604 ] }, { "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": 3, "trace": [ { "options": 10, "choice": "click element 9", "p": 0.986797480109706 }, { "options": 9, "choice": "click element 6", "p": 0.935163898358417 }, { "options": 9, "choice": "the task is complete", "p": 0.3951607387380241 } ], "latency_s": [ 0.5002939701080322, 2.450852155685425, 0.5882887840270996 ] }, { "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": 0.9994047051289965 }, { "options": 15, "choice": "click element 8", "p": 0.870263391974511 }, { "options": 15, "choice": "click element 10", "p": 0.913945924512244 }, { "options": 15, "choice": "click element 14", "p": 0.9561750762671776 }, { "options": 15, "choice": "click element 4", "p": 0.9176689854591338 }, { "options": 6, "choice": "the task is complete", "p": 0.8848988172857754 } ], "latency_s": [ 0.49639225006103516, 0.8094565868377686, 0.5927596092224121, 0.5793540477752686, 0.5639328956604004, 0.5721001625061035 ] }, { "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": 0.9994786022795508 }, { "options": 15, "choice": "click element 8", "p": 0.9203606102899532 }, { "options": 15, "choice": "click element 13", "p": 0.9597844261032407 }, { "options": 15, "choice": "click element 14", "p": 0.9282670949678353 }, { "options": 15, "choice": "click element 4", "p": 0.46122883765310485 }, { "options": 6, "choice": "the task is complete", "p": 0.743521210383342 } ], "latency_s": [ 0.4953486919403076, 0.6027894020080566, 0.579423189163208, 0.5826332569122314, 0.5949060916900635, 0.6282050609588623 ] }, { "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": 0.9957233754393379 }, { "options": 15, "choice": "click element 9", "p": 0.9575065854193904 }, { "options": 15, "choice": "click element 11", "p": 0.9572559790388527 }, { "options": 15, "choice": "click element 14", "p": 0.930744573217062 }, { "options": 15, "choice": "click element 4", "p": 0.973382480429548 }, { "options": 6, "choice": "the task is complete", "p": 0.8442762701406276 } ], "latency_s": [ 0.4999227523803711, 0.4969468116760254, 0.6787054538726807, 0.4816746711730957, 2.9809632301330566, 0.5811793804168701 ] }, { "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": 9, "trace": [ { "options": 10, "choice": "click element 7", "p": 0.9956275669495027 }, { "options": 15, "choice": "click element 12", "p": 0.9785905746975802 }, { "options": 15, "choice": "click element 14", "p": 0.9463990616575005 }, { "options": 15, "choice": "click element 4", "p": 0.8277161471226825 }, { "options": 6, "choice": "click element 4", "p": 0.4154966122860735 }, { "options": 6, "choice": "click element 3", "p": 0.40408806175107714 }, { "options": 10, "choice": "click element 3", "p": 0.4526045652195833 }, { "options": 6, "choice": "click element 4", "p": 0.8146765815687721 }, { "options": 6, "choice": "the task is complete", "p": 0.6168428119732651 } ], "latency_s": [ 0.4656839370727539, 0.5498392581939697, 0.5667057037353516, 0.5816965103149414, 0.5269441604614258, 0.08622169494628906, 0.4501030445098877, 0.44680094718933105, 0.08255648612976074 ] }, { "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": 0.9872440039223925 }, { "options": 11, "choice": "click element 7", "p": 0.9926720902015208 }, { "options": 11, "choice": "click element 9", "p": 0.9932843691656662 }, { "options": 11, "choice": "the task is complete", "p": 0.9974309451542741 } ], "latency_s": [ 0.23208975791931152, 0.5557217597961426, 0.5698106288909912, 0.48169708251953125 ] }, { "app": "settings", "seed": 12, "variant": "marks", "task": "Turn on \"Compact layout\" in the Appearance settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 3, "trace": [ { "options": 7, "choice": "click element 5", "p": 0.9971160121674013 }, { "options": 11, "choice": "click element 9", "p": 0.9801149199334758 }, { "options": 11, "choice": "the task is complete", "p": 0.3779253892485486 } ], "latency_s": [ 0.35013580322265625, 0.5652821063995361, 0.5436599254608154 ] }, { "app": "settings", "seed": 18, "variant": "marks", "task": "Turn on \"Show online status\" in the Profile settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 5, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.9989332596785224 }, { "options": 11, "choice": "click element 9", "p": 0.6602523258868719 }, { "options": 11, "choice": "click element 6", "p": 0.47171607788821396 }, { "options": 11, "choice": "click element 9", "p": 0.9245212459701172 }, { "options": 11, "choice": "the task is complete", "p": 0.43693407417393587 } ], "latency_s": [ 0.5956525802612305, 0.3268105983734131, 0.4372751712799072, 0.4193294048309326, 0.5288443565368652 ] }, { "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": 0.9997371713383423 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9996797911817045 }, { "options": 9, "choice": "the task is complete", "p": 0.9778899320582093 } ], "latency_s": [ 0.4324522018432617, 0.501676082611084, 0.5801897048950195 ] }, { "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": 0.9995583664134887 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9996334130519551 }, { "options": 9, "choice": "the task is complete", "p": 0.9792970034233545 } ], "latency_s": [ 0.4220573902130127, 0.37447047233581543, 0.591036319732666 ] }, { "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": 0.9980785586122599 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9974249341247186 }, { "options": 9, "choice": "the task is complete", "p": 0.9818277080967559 } ], "latency_s": [ 0.3502004146575928, 0.46965789794921875, 0.536548376083374 ] }, { "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": 0.999976599726147 }, { "options": 15, "choice": "click element 8: colour swatch", "p": 0.9566731675900209 }, { "options": 15, "choice": "click element 10: S (button)", "p": 0.9074072730793109 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.967318404408857 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9759164683108145 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9964293012090147 }, { "options": 6, "choice": "the task is complete", "p": 0.9363226305926786 } ], "latency_s": [ 0.36522674560546875, 0.41881465911865234, 0.41337132453918457, 0.40852832794189453, 0.38596534729003906, 0.3877537250518799, 0.4893670082092285 ] }, { "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": 0.9998031322658991 }, { "options": 15, "choice": "click element 8: colour swatch", "p": 0.984789026792966 }, { "options": 15, "choice": "click element 13: XL (button)", "p": 0.9451161443261785 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.970050068331974 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9868115484255976 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9968581322098109 }, { "options": 6, "choice": "the task is complete", "p": 0.9683476014902351 } ], "latency_s": [ 0.45887112617492676, 0.3842742443084717, 2.776323080062866, 0.354079008102417, 0.35127711296081543, 0.3529322147369385, 0.4324793815612793 ] }, { "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": 0.99979462039583 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.8917817596689325 }, { "options": 15, "choice": "click element 11: M (button)", "p": 0.9482637854030702 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9839021172216237 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9847532370786177 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9975513189486476 }, { "options": 6, "choice": "the task is complete", "p": 0.9204853022356658 } ], "latency_s": [ 0.2842245101928711, 0.3834497928619385, 0.41547632217407227, 0.35623908042907715, 0.3505122661590576, 0.32058262825012207, 0.45865845680236816 ] }, { "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": false, "steps": 10, "trace": [ { "options": 10, "choice": "click element 7: T-shirt $40 (product card)", "p": 0.9998932055224465 }, { "options": 15, "choice": "click element 12: L (button)", "p": 0.9442582541038342 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.8668764822377109 }, { "options": 15, "choice": "click element 4: Cart (0) (button)", "p": 0.9862091664778374 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9871310189635617 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.6590498619167836 }, { "options": 6, "choice": "click element 3: \u2190 Continue shopping (button)", "p": 0.38069435052844586 }, { "options": 10, "choice": "click element 7: T-shirt $40 (product card)", "p": 0.6846042526691661 }, { "options": 15, "choice": "click element 4: Cart (0) (button)", "p": 0.4493981161788064 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.8258270909209099 } ], "latency_s": [ 0.4061250686645508, 0.3478972911834717, 0.42827343940734863, 0.3424489498138428, 0.4170398712158203, 0.24425745010375977, 0.3786036968231201, 0.33043503761291504, 0.24214386940002441, 0.40938735008239746 ] }, { "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": 0.9996500632395272 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9892151365898775 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9982079899459264 }, { "options": 11, "choice": "the task is complete", "p": 0.9986657548409847 } ], "latency_s": [ 0.46747303009033203, 0.5663225650787354, 0.3383066654205322, 0.40869736671447754 ] }, { "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": 0.9996614621519828 }, { "options": 11, "choice": "click element 8: switch", "p": 0.972088834231806 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.986346179880401 }, { "options": 11, "choice": "the task is complete", "p": 0.9975711716772725 } ], "latency_s": [ 0.4236154556274414, 0.5084481239318848, 0.4755575656890869, 0.46397829055786133 ] }, { "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": 0.9997607684538005 }, { "options": 11, "choice": "click element 7: switch", "p": 0.980511620256382 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9996211043888903 }, { "options": 11, "choice": "the task is complete", "p": 0.9978560370712062 } ], "latency_s": [ 0.3074822425842285, 0.4604170322418213, 0.46743321418762207, 0.3849914073944092 ] }, { "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": 0.9620264462346815 }, { "options": 9, "choice": "click element 6", "p": 0.9534319857373246 }, { "options": 9, "choice": "click element 8", "p": 0.38163329987763545 }, { "options": 9, "choice": "the task is complete", "p": 0.969885226856648 } ], "latency_s": [ 10.645315647125244, 0.6008696556091309, 5.531010866165161, 2.506474733352661 ] }, { "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": 0.9792280186539198 }, { "options": 9, "choice": "click element 6", "p": 0.9582024445392088 }, { "options": 9, "choice": "click element 5", "p": 0.46615153335355397 }, { "options": 9, "choice": "the task is complete", "p": 0.5581503886601221 } ], "latency_s": [ 0.5160679817199707, 2.4444966316223145, 0.5910439491271973, 0.5791330337524414 ] }, { "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": 4, "trace": [ { "options": 10, "choice": "click element 5", "p": 0.9810367680496027 }, { "options": 9, "choice": "click element 6", "p": 0.9401622369162673 }, { "options": 9, "choice": "click element 5", "p": 0.6655142010764864 }, { "options": 9, "choice": "the task is complete", "p": 0.837423000996854 } ], "latency_s": [ 0.7392528057098389, 0.6130568981170654, 0.5784153938293457, 0.5673191547393799 ] }, { "app": "shop", "seed": 3, "variant": "marks", "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", "p": 0.9978471655162081 }, { "options": 15, "choice": "click element 5", "p": 0.8707491271855791 }, { "options": 15, "choice": "click element 13", "p": 0.9246896532418405 }, { "options": 15, "choice": "click element 14", "p": 0.8676765808558068 }, { "options": 15, "choice": "click element 4", "p": 0.7573213981029664 }, { "options": 6, "choice": "click element 4", "p": 0.8248363845677992 }, { "options": 6, "choice": "the task is complete", "p": 0.9387170918634724 } ], "latency_s": [ 0.5057542324066162, 0.5598771572113037, 0.5934631824493408, 0.5740137100219727, 0.5619170665740967, 0.6059272289276123, 0.6078886985778809 ] }, { "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": 0.9995157589613046 }, { "options": 15, "choice": "click element 8", "p": 0.7081357270431673 }, { "options": 15, "choice": "click element 12", "p": 0.9800440193654218 }, { "options": 15, "choice": "click element 14", "p": 0.9395769614183545 }, { "options": 15, "choice": "click element 4", "p": 0.9917872259501013 }, { "options": 6, "choice": "the task is complete", "p": 0.8261850738629394 } ], "latency_s": [ 0.4804098606109619, 0.4976694583892822, 0.6587636470794678, 0.46147775650024414, 2.9596798419952393, 0.5816044807434082 ] }, { "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": 0.999069477621147 }, { "options": 15, "choice": "click element 10", "p": 0.9535935128347093 }, { "options": 15, "choice": "click element 14", "p": 0.9495699586731455 }, { "options": 15, "choice": "click element 4", "p": 0.9022118097055344 }, { "options": 6, "choice": "the task is complete", "p": 0.6721755640368551 } ], "latency_s": [ 0.45249295234680176, 0.5296733379364014, 0.5859849452972412, 0.5618550777435303, 0.5059034824371338 ] }, { "app": "settings", "seed": 1, "variant": "marks", "task": "Turn on \"Push notifications\" in the Notifications settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 3, "trace": [ { "options": 7, "choice": "click element 4", "p": 0.9909443332859208 }, { "options": 11, "choice": "click element 9", "p": 0.935351702479474 }, { "options": 11, "choice": "the task is complete", "p": 0.6738429259439483 } ], "latency_s": [ 0.6349301338195801, 0.42202186584472656, 0.5351147651672363 ] }, { "app": "settings", "seed": 7, "variant": "marks", "task": "Turn on \"Login alerts\" in the Security settings and save the change.", "success": false, "goal_met": false, "stopped": false, "steps": 10, "trace": [ { "options": 7, "choice": "click element 4", "p": 0.9972497220255127 }, { "options": 11, "choice": "click element 9", "p": 0.9784145112803323 }, { "options": 11, "choice": "click element 9", "p": 0.5362813844437699 }, { "options": 11, "choice": "click element 4", "p": 0.578717026757383 }, { "options": 11, "choice": "click element 9", "p": 0.8127743564104409 }, { "options": 11, "choice": "click element 9", "p": 0.49559313454913734 }, { "options": 11, "choice": "click element 9", "p": 0.34415320415498213 }, { "options": 11, "choice": "click element 9", "p": 0.3938331443798896 }, { "options": 11, "choice": "click element 9", "p": 0.5886511429626605 }, { "options": 11, "choice": "click element 9", "p": 0.3584529241215967 } ], "latency_s": [ 0.48923420906066895, 0.5396428108215332, 0.4913661479949951, 0.42232179641723633, 0.5625855922698975, 0.5510618686676025, 0.3227550983428955, 0.15503287315368652, 0.30503010749816895, 0.2505006790161133 ] }, { "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": 5, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.9877604070673331 }, { "options": 11, "choice": "click element 5", "p": 0.7674839019711585 }, { "options": 11, "choice": "click element 8", "p": 0.9279060124713848 }, { "options": 11, "choice": "click element 9", "p": 0.9544744546514458 }, { "options": 11, "choice": "the task is complete", "p": 0.9935608088173739 } ], "latency_s": [ 0.49277353286743164, 0.5323855876922607, 0.5124247074127197, 0.5034358501434326, 0.5658793449401855 ] }, { "app": "settings", "seed": 19, "variant": "marks", "task": "Turn on \"Two-factor authentication\" in the Security settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 5, "trace": [ { "options": 7, "choice": "click element 6", "p": 0.9969612428582338 }, { "options": 11, "choice": "click element 9", "p": 0.5173511028205486 }, { "options": 11, "choice": "click element 6", "p": 0.5147046859025727 }, { "options": 11, "choice": "click element 9", "p": 0.8701689476721556 }, { "options": 11, "choice": "the task is complete", "p": 0.3933553087779764 } ], "latency_s": [ 0.3996593952178955, 0.3706214427947998, 0.5863473415374756, 0.4161958694458008, 0.474229097366333 ] }, { "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": 0.9976431585456494 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9985377102533419 }, { "options": 9, "choice": "the task is complete", "p": 0.9824112682630833 } ], "latency_s": [ 0.46443629264831543, 0.4302999973297119, 0.4312784671783447 ] }, { "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": 0.998563583385741 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.999703238072438 }, { "options": 9, "choice": "the task is complete", "p": 0.9913566785618464 } ], "latency_s": [ 0.30765509605407715, 0.38072800636291504, 0.40949320793151855 ] }, { "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": 0.9986477411425602 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9987697481513416 }, { "options": 9, "choice": "the task is complete", "p": 0.9855761066349027 } ], "latency_s": [ 0.31354403495788574, 0.43576550483703613, 0.5030980110168457 ] }, { "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": 0.9998707400395395 }, { "options": 15, "choice": "click element 5: colour swatch", "p": 0.6933179779253599 }, { "options": 15, "choice": "click element 13: XL (button)", "p": 0.9501754920124664 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9764179767569321 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9784719131113895 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9978356746805982 }, { "options": 6, "choice": "the task is complete", "p": 0.9206377209753304 } ], "latency_s": [ 0.32282423973083496, 2.767759323120117, 0.3522765636444092, 0.35994982719421387, 0.3344440460205078, 0.43467283248901367, 0.3624763488769531 ] }, { "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": 0.9999754220954641 }, { "options": 15, "choice": "click element 8: colour swatch", "p": 0.7945290871094611 }, { "options": 15, "choice": "click element 12: L (button)", "p": 0.9390508918787793 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9590168214761953 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9953791311433425 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9968855926936391 }, { "options": 6, "choice": "the task is complete", "p": 0.9429529665035707 } ], "latency_s": [ 0.30607175827026367, 0.4138484001159668, 0.34592509269714355, 0.35906362533569336, 0.458510160446167, 0.32916927337646484, 0.46906399726867676 ] }, { "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": false, "steps": 10, "trace": [ { "options": 10, "choice": "click element 5: Cap $26 (product card)", "p": 0.9999832321186285 }, { "options": 15, "choice": "click element 10: S (button)", "p": 0.9471457180051523 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9810668378488968 }, { "options": 15, "choice": "click element 4: Cart (0) (button)", "p": 0.9577131912061004 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9774508866412739 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.731293434802697 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.4439582360200907 }, { "options": 6, "choice": "click element 3: \u2190 Continue shopping (button)", "p": 0.328358463123822 }, { "options": 10, "choice": "click element 5: Cap $26 (product card)", "p": 0.5622133110644684 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.4672495099040733 } ], "latency_s": [ 0.25352907180786133, 0.4239339828491211, 0.3431365489959717, 0.4048128128051758, 0.40848684310913086, 0.38098669052124023, 0.3507845401763916, 0.0755150318145752, 0.39914703369140625, 0.40430212020874023 ] }, { "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": 0.9995896176245779 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9720458245728442 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9980286683527613 }, { "options": 11, "choice": "the task is complete", "p": 0.9949838452577184 } ], "latency_s": [ 0.07826089859008789, 0.35942554473876953, 0.3331325054168701, 0.4168856143951416 ] }, { "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": 0.9982904862686999 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9801944793125247 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.989294385879283 }, { "options": 11, "choice": "the task is complete", "p": 0.984287825889 } ], "latency_s": [ 0.4188201427459717, 0.4915790557861328, 0.46778059005737305, 0.46413278579711914 ] }, { "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": 0.9986831575760067 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9752077312815891 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.983993886149451 }, { "options": 11, "choice": "the task is complete", "p": 0.9961503983618577 } ], "latency_s": [ 0.2871851921081543, 0.4607102870941162, 0.4571826457977295, 0.3839750289916992 ] }, { "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": 0.9998444366231647 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9879159200711515 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9975948290591056 }, { "options": 11, "choice": "the task is complete", "p": 0.9987889519368166 } ], "latency_s": [ 0.10500502586364746, 0.36197781562805176, 0.3738834857940674, 0.36542367935180664 ] }, { "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": 4, "trace": [ { "options": 10, "choice": "click element 8", "p": 0.9745218971584338 }, { "options": 9, "choice": "click element 6", "p": 0.8998874944134162 }, { "options": 9, "choice": "click element 8", "p": 0.3909850136529012 }, { "options": 9, "choice": "the task is complete", "p": 0.9308504148373363 } ], "latency_s": [ 10.678183794021606, 0.6102313995361328, 5.543504238128662, 2.5096664428710938 ] }, { "app": "mail", "seed": 12, "variant": "marks", "task": "Archive the email from David Kim about the lunch on Friday.", "success": false, "goal_met": false, "stopped": true, "steps": 4, "trace": [ { "options": 10, "choice": "click element 5", "p": 0.1958112299840454 }, { "options": 9, "choice": "click element 6", "p": 0.9663843581040478 }, { "options": 9, "choice": "click element 8", "p": 0.3747590182756255 }, { "options": 9, "choice": "the task is complete", "p": 0.964926079388293 } ], "latency_s": [ 0.5007364749908447, 2.4451944828033447, 0.5908877849578857, 0.5736567974090576 ] }, { "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": 6, "trace": [ { "options": 10, "choice": "click element 5", "p": 0.9801893011428631 }, { "options": 9, "choice": "click element 6", "p": 0.9540033244524807 }, { "options": 9, "choice": "click element 5", "p": 0.5737068640105633 }, { "options": 9, "choice": "click element 6", "p": 0.6239131862540288 }, { "options": 8, "choice": "click element 5", "p": 0.5382046712674701 }, { "options": 9, "choice": "the task is complete", "p": 0.5993865632230986 } ], "latency_s": [ 0.7261807918548584, 0.6152627468109131, 0.5568797588348389, 0.570850133895874, 0.5954415798187256, 0.5629141330718994 ] }, { "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": 0.9992209709927525 }, { "options": 15, "choice": "click element 9", "p": 0.9881832697799228 }, { "options": 15, "choice": "click element 12", "p": 0.9746578248955571 }, { "options": 15, "choice": "click element 14", "p": 0.930727643942461 }, { "options": 15, "choice": "click element 4", "p": 0.9872583302570186 }, { "options": 6, "choice": "the task is complete", "p": 0.8809410547060627 } ], "latency_s": [ 0.5280895233154297, 0.5735304355621338, 0.5625298023223877, 0.5876920223236084, 0.6109328269958496, 0.5713014602661133 ] }, { "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": 0.999184035550947 }, { "options": 15, "choice": "click element 7", "p": 0.8739420963036869 }, { "options": 15, "choice": "click element 11", "p": 0.9819631097096669 }, { "options": 15, "choice": "click element 14", "p": 0.9640603560227202 }, { "options": 15, "choice": "click element 4", "p": 0.9898319603984171 }, { "options": 6, "choice": "the task is complete", "p": 0.73733090171527 } ], "latency_s": [ 0.42960286140441895, 0.656806230545044, 0.4741702079772949, 2.977264642715454, 0.573110818862915, 0.5398135185241699 ] }, { "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": 0.999150944770012 }, { "options": 15, "choice": "click element 5", "p": 0.7936651061947863 }, { "options": 15, "choice": "click element 10", "p": 0.838382507635873 }, { "options": 15, "choice": "click element 14", "p": 0.8975989398928305 }, { "options": 15, "choice": "click element 4", "p": 0.9585684783699854 }, { "options": 6, "choice": "the task is complete", "p": 0.8363475327792819 } ], "latency_s": [ 0.48749256134033203, 0.5780539512634277, 0.5591006278991699, 0.5205283164978027, 0.6985406875610352, 0.44476842880249023 ] }, { "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": 0.9940478254792573 }, { "options": 11, "choice": "click element 8", "p": 0.9680595135011586 }, { "options": 11, "choice": "click element 9", "p": 0.9977030377119199 }, { "options": 11, "choice": "the task is complete", "p": 0.9969029141353869 } ], "latency_s": [ 0.4799308776855469, 0.5650358200073242, 0.5721828937530518, 0.4703202247619629 ] }, { "app": "settings", "seed": 8, "variant": "marks", "task": "Turn on \"Compact layout\" in the Appearance settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 8, "trace": [ { "options": 7, "choice": "click element 5", "p": 0.9880453740821733 }, { "options": 11, "choice": "click element 9", "p": 0.9698665585038334 }, { "options": 11, "choice": "click element 9", "p": 0.5408175718646441 }, { "options": 11, "choice": "click element 5", "p": 0.3313249542659607 }, { "options": 11, "choice": "click element 9", "p": 0.9498367228725045 }, { "options": 11, "choice": "click element 5", "p": 0.42140746061554035 }, { "options": 11, "choice": "click element 9", "p": 0.6070284273795111 }, { "options": 11, "choice": "the task is complete", "p": 0.6875034279387744 } ], "latency_s": [ 0.3593924045562744, 0.5594267845153809, 0.5485777854919434, 0.12592673301696777, 0.3555305004119873, 0.32159876823425293, 0.4279179573059082, 0.4218556880950928 ] }, { "app": "settings", "seed": 14, "variant": "marks", "task": "Turn on \"Dark mode\" in the Appearance settings and save the change.", "success": false, "goal_met": false, "stopped": true, "steps": 6, "trace": [ { "options": 7, "choice": "click element 5", "p": 0.9880817420552599 }, { "options": 11, "choice": "click element 9", "p": 0.7769692082339661 }, { "options": 11, "choice": "click element 9", "p": 0.5711583443863535 }, { "options": 11, "choice": "click element 5", "p": 0.5438014611321522 }, { "options": 11, "choice": "click element 9", "p": 0.9562210242569862 }, { "options": 11, "choice": "the task is complete", "p": 0.5476263703872764 } ], "latency_s": [ 0.4584157466888428, 0.5094661712646484, 0.5022001266479492, 0.5746378898620605, 0.4673912525177002, 0.3694312572479248 ] }, { "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": 0.6326158621978405 }, { "options": 11, "choice": "click element 7", "p": 0.9943720522767634 }, { "options": 11, "choice": "click element 9", "p": 0.9975135843396358 }, { "options": 11, "choice": "the task is complete", "p": 0.9979995747146981 } ], "latency_s": [ 0.5469002723693848, 0.4243936538696289, 0.46785783767700195, 0.5603914260864258 ] }, { "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": 0.998934795251896 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9972709586363404 }, { "options": 9, "choice": "the task is complete", "p": 0.9948523087029575 } ], "latency_s": [ 0.3558359146118164, 0.42853426933288574, 0.39093828201293945 ] }, { "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": 0.9990232869284298 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9999328330640964 }, { "options": 9, "choice": "the task is complete", "p": 0.9950170020503021 } ], "latency_s": [ 0.32662391662597656, 0.39082956314086914, 0.3811826705932617 ] }, { "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": 0.9994790986951919 }, { "options": 9, "choice": "click element 6: Archive (button)", "p": 0.9975000583749095 }, { "options": 9, "choice": "the task is complete", "p": 0.9809050967338991 } ], "latency_s": [ 0.40529394149780273, 0.4709627628326416, 0.39199113845825195 ] }, { "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": 0.9999747904998781 }, { "options": 15, "choice": "click element 9: colour swatch", "p": 0.9912425406562277 }, { "options": 15, "choice": "click element 12: L (button)", "p": 0.9606975329197182 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9636139133404757 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9836745033288585 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9982927774400868 }, { "options": 6, "choice": "the task is complete", "p": 0.9207516407800123 } ], "latency_s": [ 2.6928348541259766, 0.3613474369049072, 0.35785675048828125, 0.34207582473754883, 0.4246683120727539, 0.36353182792663574, 0.3785586357116699 ] }, { "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": 0.999974612484399 }, { "options": 15, "choice": "click element 7: colour swatch", "p": 0.9093039874932068 }, { "options": 15, "choice": "click element 11: M (button)", "p": 0.9193449601674573 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9766880088375389 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9887680085637847 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9955213198054456 }, { "options": 6, "choice": "the task is complete", "p": 0.9716914068390711 } ], "latency_s": [ 0.34256887435913086, 0.34452366828918457, 0.3515012264251709, 0.4589576721191406, 0.3231019973754883, 0.4705071449279785, 0.3438255786895752 ] }, { "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": 0.9999222848313496 }, { "options": 15, "choice": "click element 5: colour swatch", "p": 0.8496668514506132 }, { "options": 15, "choice": "click element 10: S (button)", "p": 0.9062843897872591 }, { "options": 15, "choice": "click element 14: Add to cart (button)", "p": 0.9797023873058333 }, { "options": 15, "choice": "click element 4: Cart (1) (button)", "p": 0.9873498511074769 }, { "options": 6, "choice": "click element 4: Checkout (button)", "p": 0.9975615319879845 }, { "options": 6, "choice": "the task is complete", "p": 0.9200320352483686 } ], "latency_s": [ 0.34515810012817383, 0.3463878631591797, 0.41554808616638184, 0.39594173431396484, 0.35695481300354004, 0.3447263240814209, 0.6522634029388428 ] }, { "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": 0.9997048157108188 }, { "options": 11, "choice": "click element 8: switch", "p": 0.972055155557427 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.997769737875076 }, { "options": 11, "choice": "the task is complete", "p": 0.9984116067743946 } ], "latency_s": [ 0.48559021949768066, 0.5620622634887695, 0.33147382736206055, 0.41985416412353516 ] }, { "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": 0.9996739021916611 }, { "options": 11, "choice": "click element 8: switch", "p": 0.9720221393521392 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9890069944301108 }, { "options": 11, "choice": "the task is complete", "p": 0.9974111291737081 } ], "latency_s": [ 0.4189891815185547, 0.4998934268951416, 0.47321605682373047, 0.4670240879058838 ] }, { "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": 0.9990385506050415 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9827102330183639 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9997179970576149 }, { "options": 11, "choice": "the task is complete", "p": 0.997201054281302 } ], "latency_s": [ 0.2861156463623047, 0.467970609664917, 0.44588136672973633, 0.3788027763366699 ] }, { "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": 0.9989126026980848 }, { "options": 11, "choice": "click element 7: switch", "p": 0.9843468172160512 }, { "options": 11, "choice": "click element 9: Save changes (button)", "p": 0.9976416024291495 }, { "options": 11, "choice": "the task is complete", "p": 0.9983947185486056 } ], "latency_s": [ 0.09914040565490723, 0.3495900630950928, 0.3771800994873047, 0.3699612617492676 ] } ] }