11 KiB
11 KiB
| 1 | model | baseline | metric | point_delta | bootstrap_median_delta | ci_2_5 | ci_97_5 | replicates | unit |
|---|---|---|---|---|---|---|---|---|---|
| 2 | C1 | C0 | accuracy | 0.015109890109890056 | 0.014540654071697634 | -0.02072183396214814 | 0.0508771724181045 | 1000 | paired source-video group resample |
| 3 | C1 | C0 | macro_f1 | -0.004691729310120518 | -0.005934296634649006 | -0.04397414179686003 | 0.03565646614122406 | 1000 | paired source-video group resample |
| 4 | C1 | C0 | mae | -0.0554240345954895 | -0.05444282293319702 | -0.09375483095645905 | -0.01503600478172303 | 1000 | paired source-video group resample |
| 5 | C1 | C0 | rmse | -0.014935817346632296 | -0.013258818758929702 | -0.06884780543374597 | 0.046824820732205875 | 1000 | paired source-video group resample |
| 6 | C1 | C0 | pearson | 0.05875682830810547 | 0.05802242457866669 | 0.002364498376846314 | 0.1096881166100502 | 1000 | paired source-video group resample |
| 7 | C1 | C0 | interval_90_coverage | -0.013736263736263687 | -0.01407375396139443 | -0.04065771954245597 | 0.011025889100001162 | 1000 | paired source-video group resample |
| 8 | C1 | C0 | interval_90_mean_width | -0.6801879405975342 | -0.6815143823623657 | -0.7549685001373291 | -0.5937675774097443 | 1000 | paired source-video group resample |
| 9 | C2 | C0 | accuracy | 0.005494505494505475 | 0.005369214581201265 | -0.02994376576360175 | 0.0391940871501641 | 1000 | paired source-video group resample |
| 10 | C2 | C0 | macro_f1 | -0.07956378757630245 | -0.0790228080874627 | -0.11503642522479199 | -0.04535533337167957 | 1000 | paired source-video group resample |
| 11 | C2 | C0 | mae | -0.0174868106842041 | -0.01701989769935608 | -0.05516543835401535 | 0.02024096548557281 | 1000 | paired source-video group resample |
| 12 | C2 | C0 | rmse | 0.01013764645327897 | 0.009857838331185975 | -0.04068845414232331 | 0.06170280906214439 | 1000 | paired source-video group resample |
| 13 | C2 | C0 | pearson | 0.06041759252548218 | 0.05996474623680115 | 0.012590093165636064 | 0.10714993029832838 | 1000 | paired source-video group resample |
| 14 | C2 | C0 | interval_90_coverage | -0.01098901098901095 | -0.010906617201527025 | -0.036017915080268074 | 0.012361034956431066 | 1000 | paired source-video group resample |
| 15 | C2 | C0 | interval_90_mean_width | -0.5603723526000977 | -0.5623085498809814 | -0.6364005088806153 | -0.4799393117427826 | 1000 | paired source-video group resample |
| 16 | C3 | C0 | accuracy | 0.016483516483516425 | 0.016563344218070708 | -0.01763847840925233 | 0.050214192879048734 | 1000 | paired source-video group resample |
| 17 | C3 | C0 | macro_f1 | -0.058533700572424185 | -0.058234548423185234 | -0.09561566579622569 | -0.02038892280273245 | 1000 | paired source-video group resample |
| 18 | C3 | C0 | mae | -0.016335368156433105 | -0.015149623155593872 | -0.055715514719486235 | 0.025416558980941768 | 1000 | paired source-video group resample |
| 19 | C3 | C0 | rmse | 0.014782920551098089 | 0.015419141692077643 | -0.038076123069670856 | 0.07340071085319849 | 1000 | paired source-video group resample |
| 20 | C3 | C0 | pearson | 0.07739311456680298 | 0.07681527733802795 | 0.024015167355537416 | 0.12345541119575498 | 1000 | paired source-video group resample |
| 21 | C3 | C0 | interval_90_coverage | -0.0027472527472527375 | -0.00410961988830838 | -0.027750467750793536 | 0.020954891616959875 | 1000 | paired source-video group resample |
| 22 | C3 | C0 | interval_90_mean_width | -0.640167236328125 | -0.6405612230300903 | -0.7109949052333832 | -0.5546378016471862 | 1000 | paired source-video group resample |
| 23 | C4 | C0 | accuracy | 0.016483516483516425 | 0.016415899393667166 | -0.017356716818758812 | 0.04911759336909525 | 1000 | paired source-video group resample |
| 24 | C4 | C0 | macro_f1 | -0.0008760072279735409 | -0.0006209418412993495 | -0.03810678311317003 | 0.036679564307315324 | 1000 | paired source-video group resample |
| 25 | C4 | C0 | mae | -0.04160189628601074 | -0.04116714000701904 | -0.07862299531698227 | -0.0037129849195480426 | 1000 | paired source-video group resample |
| 26 | C4 | C0 | rmse | 0.014384588646868646 | 0.01554152399820774 | -0.041543071226566815 | 0.08196211635437033 | 1000 | paired source-video group resample |
| 27 | C4 | C0 | pearson | 0.04924803972244263 | 0.04813617467880249 | -0.013162557780742644 | 0.10131643265485762 | 1000 | paired source-video group resample |
| 28 | C4 | C0 | interval_90_coverage | -0.01098901098901095 | -0.01134751773049647 | -0.03755502866983134 | 0.01479151957106922 | 1000 | paired source-video group resample |
| 29 | C4 | C0 | interval_90_mean_width | -0.6055305004119873 | -0.606930136680603 | -0.6910651624202728 | -0.5102817654609682 | 1000 | paired source-video group resample |
| 30 | C5 | C0 | accuracy | 0.02335164835164838 | 0.0231607629427793 | -0.007834704176513621 | 0.05665799312178082 | 1000 | paired source-video group resample |
| 31 | C5 | C0 | macro_f1 | -0.011379078722261737 | -0.011081368136203418 | -0.05078514978285897 | 0.03206592123232569 | 1000 | paired source-video group resample |
| 32 | C5 | C0 | mae | -0.07105213403701782 | -0.07029640674591064 | -0.1101970300078392 | -0.033040848374366764 | 1000 | paired source-video group resample |
| 33 | C5 | C0 | rmse | -0.043829951679029255 | -0.04314210307825145 | -0.09518903687579511 | 0.008231764878183861 | 1000 | paired source-video group resample |
| 34 | C5 | C0 | pearson | 0.09820222854614258 | 0.09711459279060364 | 0.054920969903469084 | 0.14132471680641173 | 1000 | paired source-video group resample |
| 35 | C5 | C0 | interval_90_coverage | -0.016483516483516425 | -0.016346749476701616 | -0.041550262655205374 | 0.006870169627622198 | 1000 | paired source-video group resample |
| 36 | C5 | C0 | interval_90_mean_width | -0.7618138790130615 | -0.7637132406234741 | -0.8362245619297027 | -0.6784132480621338 | 1000 | paired source-video group resample |
| 37 | C6 | C0 | accuracy | 0.03434065934065933 | 0.03507210334215988 | 0.0013193504736129726 | 0.06677418151987477 | 1000 | paired source-video group resample |
| 38 | C6 | C0 | macro_f1 | 0.02417681475733191 | 0.0245627409794269 | -0.012247590393776613 | 0.0609586676069792 | 1000 | paired source-video group resample |
| 39 | C6 | C0 | mae | -0.08769041299819946 | -0.08800148963928223 | -0.12380164712667466 | -0.051559735834598545 | 1000 | paired source-video group resample |
| 40 | C6 | C0 | rmse | -0.0557666607442967 | -0.05718944521581815 | -0.10411016254737489 | -0.011209869721099662 | 1000 | paired source-video group resample |
| 41 | C6 | C0 | pearson | 0.0964621901512146 | 0.09742751717567444 | 0.0543783888220787 | 0.1401650607585907 | 1000 | paired source-video group resample |
| 42 | C6 | C0 | interval_90_coverage | -0.02335164835164838 | -0.024096397645309686 | -0.04845282656595448 | 0.0 | 1000 | paired source-video group resample |
| 43 | C6 | C0 | interval_90_mean_width | -0.8398799896240234 | -0.8415627479553223 | -0.8992792367935181 | -0.7717564046382904 | 1000 | paired source-video group resample |
| 44 | C6_no_distance | C0 | accuracy | 0.012362637362637319 | 0.011665591419527832 | -0.021922349201543952 | 0.0445976159085915 | 1000 | paired source-video group resample |
| 45 | C6_no_distance | C0 | macro_f1 | -0.041443005147987155 | -0.042715995881111246 | -0.0793164931295086 | -0.0021521221408520616 | 1000 | paired source-video group resample |
| 46 | C6_no_distance | C0 | mae | -0.05394166707992554 | -0.05345669388771057 | -0.08995662033557891 | -0.017440022528171555 | 1000 | paired source-video group resample |
| 47 | C6_no_distance | C0 | rmse | -0.027334657615164293 | -0.027400945882898098 | -0.07395318523759227 | 0.020861843239490783 | 1000 | paired source-video group resample |
| 48 | C6_no_distance | C0 | pearson | 0.08535701036453247 | 0.08517509698867798 | 0.04233360141515732 | 0.12865879982709885 | 1000 | paired source-video group resample |
| 49 | C6_no_distance | C0 | interval_90_coverage | -0.02335164835164838 | -0.023421019727422 | -0.04858552631578949 | -0.0012778505897772484 | 1000 | paired source-video group resample |
| 50 | C6_no_distance | C0 | interval_90_mean_width | -0.845958948135376 | -0.8460291624069214 | -0.8988584756851197 | -0.7863011598587036 | 1000 | paired source-video group resample |
| 51 | C6_no_reconstruction | C0 | accuracy | 0.008241758241758212 | 0.007412935104671281 | -0.02508586214016911 | 0.041334712950600795 | 1000 | paired source-video group resample |
| 52 | C6_no_reconstruction | C0 | macro_f1 | -0.038098823880311605 | -0.0380264210091098 | -0.07862970799872031 | 0.0008047696861085368 | 1000 | paired source-video group resample |
| 53 | C6_no_reconstruction | C0 | mae | -0.03766679763793945 | -0.037051618099212646 | -0.07584996074438095 | 0.001131595671176908 | 1000 | paired source-video group resample |
| 54 | C6_no_reconstruction | C0 | rmse | -0.004467192313314605 | -0.004141038354871618 | -0.06167746651854182 | 0.05485222799945723 | 1000 | paired source-video group resample |
| 55 | C6_no_reconstruction | C0 | pearson | 0.06950116157531738 | 0.06919342279434204 | 0.01576427072286606 | 0.12347625344991682 | 1000 | paired source-video group resample |
| 56 | C6_no_reconstruction | C0 | interval_90_coverage | -0.016483516483516425 | -0.01702685733498932 | -0.044414535666218 | 0.008291378102871401 | 1000 | paired source-video group resample |
| 57 | C6_no_reconstruction | C0 | interval_90_mean_width | -0.7536470890045166 | -0.7535206079483032 | -0.8238759577274323 | -0.6792047619819641 | 1000 | paired source-video group resample |
| 58 | C6_pointmask | C0 | accuracy | 0.01098901098901095 | 0.010928982145223365 | -0.021508282476024394 | 0.04276060564095464 | 1000 | paired source-video group resample |
| 59 | C6_pointmask | C0 | macro_f1 | -0.004597019933230584 | -0.004950783837691097 | -0.04252592927395962 | 0.03481194374641572 | 1000 | paired source-video group resample |
| 60 | C6_pointmask | C0 | mae | -0.03887361288070679 | -0.03850683569908142 | -0.07904898971319199 | 0.0024588942527770732 | 1000 | paired source-video group resample |
| 61 | C6_pointmask | C0 | rmse | 0.018223692242232525 | 0.01828771010893937 | -0.03897288944724318 | 0.07443797524234813 | 1000 | paired source-video group resample |
| 62 | C6_pointmask | C0 | pearson | 0.04544329643249512 | 0.04554110765457153 | -0.009580320119857787 | 0.09693647027015685 | 1000 | paired source-video group resample |
| 63 | C6_pointmask | C0 | interval_90_coverage | -0.009615384615384581 | -0.010281847013516643 | -0.034839457133399594 | 0.015473493244019835 | 1000 | paired source-video group resample |
| 64 | C6_pointmask | C0 | interval_90_mean_width | -0.6530871391296387 | -0.6545566320419312 | -0.7273817896842957 | -0.5680322289466858 | 1000 | paired source-video group resample |
| 65 | C7_distill | C0 | accuracy | -0.0013736263736263687 | -0.0025957181599204904 | -0.03561744768641323 | 0.03287716294160066 | 1000 | paired source-video group resample |
| 66 | C7_distill | C0 | macro_f1 | -0.03154995832206664 | -0.031907844496559035 | -0.07075084408889719 | 0.01119856559020494 | 1000 | paired source-video group resample |
| 67 | C7_distill | C0 | mae | -0.0591282844543457 | -0.05798792839050293 | -0.09516946226358414 | -0.022455814480781554 | 1000 | paired source-video group resample |
| 68 | C7_distill | C0 | rmse | -0.039041818430481046 | -0.03907461260298151 | -0.08993284952634278 | 0.01886223576934703 | 1000 | paired source-video group resample |
| 69 | C7_distill | C0 | pearson | 0.08209490776062012 | 0.081440269947052 | 0.029983995854854586 | 0.12790912091732023 | 1000 | paired source-video group resample |
| 70 | C7_distill | C0 | interval_90_coverage | -0.04258241758241754 | -0.0430177622632516 | -0.069833904006728 | -0.016924193577931214 | 1000 | paired source-video group resample |
| 71 | C7_distill | C0 | interval_90_mean_width | -0.8419189453125 | -0.8431320190429688 | -0.9057650566101074 | -0.7694313526153564 | 1000 | paired source-video group resample |
| 72 | C7_group | C0 | accuracy | 0.016483516483516425 | 0.01578569810465902 | -0.017397203855622368 | 0.04950699615416091 | 1000 | paired source-video group resample |
| 73 | C7_group | C0 | macro_f1 | -0.0442503179504562 | -0.045386474713565494 | -0.08299241213109994 | -0.0069366953513426265 | 1000 | paired source-video group resample |
| 74 | C7_group | C0 | mae | -0.04738658666610718 | -0.046143680810928345 | -0.08319220691919327 | -0.007835713028907778 | 1000 | paired source-video group resample |
| 75 | C7_group | C0 | rmse | -0.011885811847952454 | -0.010572588059510002 | -0.06285378747754637 | 0.04485988704499218 | 1000 | paired source-video group resample |
| 76 | C7_group | C0 | pearson | 0.07194912433624268 | 0.06962910294532776 | 0.025362481176853184 | 0.11925912424921989 | 1000 | paired source-video group resample |
| 77 | C7_group | C0 | interval_90_coverage | -0.016483516483516425 | -0.01619944693058395 | -0.04283849684452092 | 0.007804650605708006 | 1000 | paired source-video group resample |
| 78 | C7_group | C0 | interval_90_mean_width | -0.6982431411743164 | -0.6987943649291992 | -0.765870851278305 | -0.6182706952095032 | 1000 | paired source-video group resample |