Files
aituner/runs/frontier-attn-structured-v0/results/trace-verdict.csv

8.4 KiB

1cellmetricquantileold_biasnew_biasabs_bias_delta_ppvalidity
2tp1_rho0p00125ttftmean-0.13461915993830945-0.06328385143753473-7.133530850077471GATE_FAIL_DIAGNOSTIC
3tp1_rho0p00125ttftp50-0.1888032883165517-0.1117698463137391-7.7033442002812595GATE_FAIL_DIAGNOSTIC
4tp1_rho0p00125ttftp90-0.23223319000679374-0.0884727580604037-14.376043194639005GATE_FAIL_DIAGNOSTIC
5tp1_rho0p00125ttftp99-0.16824856840168442-0.08585570369326061-8.239286470842382GATE_FAIL_DIAGNOSTIC
6tp1_rho0p00125tpotmean0.13056538761782690.143038982596282171.2473594978455265GATE_FAIL_DIAGNOSTIC
7tp1_rho0p00125tpotp500.168379917780634550.16887801449913090.04980967184963492GATE_FAIL_DIAGNOSTIC
8tp1_rho0p00125tpotp900.0128555644229329540.022938412555164591.0082848132231637GATE_FAIL_DIAGNOSTIC
9tp1_rho0p00125tpotp99-0.08151080694091946-0.06480973978913974-1.6701067151779714GATE_FAIL_DIAGNOSTIC
10tp1_rho0p00125e2emean0.065391574366393410.08380949064265251.8417916276259092GATE_FAIL_DIAGNOSTIC
11tp1_rho0p00125e2ep500.108679341717559540.111421880990865060.2742539273305519GATE_FAIL_DIAGNOSTIC
12tp1_rho0p00125e2ep900.109461791609340730.118726071781761050.9264280172420314GATE_FAIL_DIAGNOSTIC
13tp1_rho0p00125e2ep99-0.0657146472433028-0.04585643943465822-1.9858207808644577GATE_FAIL_DIAGNOSTIC
14tp1_rho0p0025ttftmean-0.17677087458166194-0.09487906467830536-8.189180990335657GATE_FAIL_DIAGNOSTIC
15tp1_rho0p0025ttftp500.0083114361472725660.0155086354583771750.7197199311104608GATE_FAIL_DIAGNOSTIC
16tp1_rho0p0025ttftp90-0.2608553178054708-0.129865645852306-13.098967195316478GATE_FAIL_DIAGNOSTIC
17tp1_rho0p0025ttftp99-0.22116442296103195-0.14410151018893788-7.706291277209407GATE_FAIL_DIAGNOSTIC
18tp1_rho0p0025tpotmean0.0143807336824301420.0523028601773065443.7922126494876403GATE_FAIL_DIAGNOSTIC
19tp1_rho0p0025tpotp500.133511459638777060.142441541949991650.8930082311214588GATE_FAIL_DIAGNOSTIC
20tp1_rho0p0025tpotp90-0.054569501304381050.018069551387063856-3.649994991731719GATE_FAIL_DIAGNOSTIC
21tp1_rho0p0025tpotp99-0.23635406197836167-0.1790206784227079-5.733338355565376GATE_FAIL_DIAGNOSTIC
22tp1_rho0p0025e2emean-0.0201641899834414520.01563919326555167-0.4524996717889782GATE_FAIL_DIAGNOSTIC
23tp1_rho0p0025e2ep500.076328158517957420.105059515943209182.8731357425251765GATE_FAIL_DIAGNOSTIC
24tp1_rho0p0025e2ep900.0498090090429463350.081656074751459533.1847065708513194GATE_FAIL_DIAGNOSTIC
25tp1_rho0p0025e2ep99-0.18303183751478602-0.15333409130015813-2.96977462146279GATE_FAIL_DIAGNOSTIC
26tp2_rho0p0025ttftmean-0.11161154024124531-0.045433491316312524-6.617804892493279PASS_SUBCRITICAL
27tp2_rho0p0025ttftp50-0.18420934047220774-0.0875990583320057-9.661028214020204PASS_SUBCRITICAL
28tp2_rho0p0025ttftp90-0.21836264490202395-0.1142200855839675-10.414255931805645PASS_SUBCRITICAL
29tp2_rho0p0025ttftp99-0.17283197594971011-0.07674087497700505-9.609110097270507PASS_SUBCRITICAL
30tp2_rho0p0025tpotmean0.137114990814875630.150737099786897781.362210897202215PASS_SUBCRITICAL
31tp2_rho0p0025tpotp500.175553213053084880.185272859254059480.9719646200974597PASS_SUBCRITICAL
32tp2_rho0p0025tpotp900.05915799751373380.078639967685883541.9481970172149734PASS_SUBCRITICAL
33tp2_rho0p0025tpotp990.13004836750916330.16619953971259183.6151172203428503PASS_SUBCRITICAL
34tp2_rho0p0025e2emean0.109253538652578750.126961461540309771.7707922887731016PASS_SUBCRITICAL
35tp2_rho0p0025e2ep500.13391656007554080.147962511841797121.404595176625631PASS_SUBCRITICAL
36tp2_rho0p0025e2ep900.106668287246645390.127672359866046222.1004072619400835PASS_SUBCRITICAL
37tp2_rho0p0025e2ep99-0.07437942975605877-0.03965040123988098-3.472902851617779PASS_SUBCRITICAL
38tp2_rho0p005ttftmean-0.14129871969878843-0.07082500585057615-7.047371384821228GATE_FAIL_DIAGNOSTIC
39tp2_rho0p005ttftp50-0.2042045530944649-0.1284088888361358-7.579566425832909GATE_FAIL_DIAGNOSTIC
40tp2_rho0p005ttftp90-0.19003454588767263-0.111136573344055-7.889797254361763GATE_FAIL_DIAGNOSTIC
41tp2_rho0p005ttftp99-0.19373351009539902-0.09012556161973535-10.360794847566366GATE_FAIL_DIAGNOSTIC
42tp2_rho0p005tpotmean0.031173374385620040.054573365990278762.3399991604658723GATE_FAIL_DIAGNOSTIC
43tp2_rho0p005tpotp500.076682495973021820.08725121462778951.0568718654767675GATE_FAIL_DIAGNOSTIC
44tp2_rho0p005tpotp90-0.037248276584296210.01132352325010614-2.5924753334190074GATE_FAIL_DIAGNOSTIC
45tp2_rho0p005tpotp99-0.10050436157089844-0.05948329733667248-4.102106423422596GATE_FAIL_DIAGNOSTIC
46tp2_rho0p005e2emean0.0238678076249164950.0501642367599080752.629642913499158GATE_FAIL_DIAGNOSTIC
47tp2_rho0p005e2ep500.075366681312788510.09124939943959781.588271812680929GATE_FAIL_DIAGNOSTIC
48tp2_rho0p005e2ep90-0.03100470462321266-0.0004979191794830456-3.0506785443729614GATE_FAIL_DIAGNOSTIC
49tp2_rho0p005e2ep99-0.04909581632382212-0.0014369075488634014-4.765890877495872GATE_FAIL_DIAGNOSTIC
50tp4_rho0p0025ttftmean0.0250225747382772820.077666465650613465.2643890912336175PASS_SUBCRITICAL
51tp4_rho0p0025ttftp50-0.0400421718462774250.029153379043297147-1.0888792802980278PASS_SUBCRITICAL
52tp4_rho0p0025ttftp90-0.0562300976343826160.025222989748299444-3.100710788608317PASS_SUBCRITICAL
53tp4_rho0p0025ttftp99-0.075354780891279730.0205549324689376-5.479984842234213PASS_SUBCRITICAL
54tp4_rho0p0025tpotmean0.21702326181031440.22951700167958411.2493739869269715PASS_SUBCRITICAL
55tp4_rho0p0025tpotp500.224067510049369170.224069406109588420.00018960602192474862PASS_SUBCRITICAL
56tp4_rho0p0025tpotp900.17256684920415520.17959654833855460.7029699134399409PASS_SUBCRITICAL
57tp4_rho0p0025tpotp990.16037643347945790.2541994509270489.382301744759008PASS_SUBCRITICAL
58tp4_rho0p0025e2emean0.183280794553787760.191906604761045540.8625810207257778PASS_SUBCRITICAL
59tp4_rho0p0025e2ep500.20571096156964040.212532423006942860.6821461437302473PASS_SUBCRITICAL
60tp4_rho0p0025e2ep900.18697038792116480.192798559166665360.5828171245500557PASS_SUBCRITICAL
61tp4_rho0p0025e2ep990.148383040658856550.151605883464990270.3222842806133719PASS_SUBCRITICAL
62tp4_rho0p005ttftmean0.0286488799976389630.083569735193791255.492085519615229PASS_SUBCRITICAL
63tp4_rho0p005ttftp500.0282379791905828760.090213247371931116.197526818134823PASS_SUBCRITICAL
64tp4_rho0p005ttftp90-0.055961238578361966-0.0006012940489499138-5.535994452941205PASS_SUBCRITICAL
65tp4_rho0p005ttftp99-0.0454911876151101460.052537086841942050.7045899226831902PASS_SUBCRITICAL
66tp4_rho0p005tpotmean0.17071939366235110.18135068190612291.0631288243771824PASS_SUBCRITICAL
67tp4_rho0p005tpotp500.168513748590253170.17433245392486050.5818705334607321PASS_SUBCRITICAL
68tp4_rho0p005tpotp900.104926213536268640.118168229071557441.3242015535288796PASS_SUBCRITICAL
69tp4_rho0p005tpotp990.312318887694717660.36622672017044735.390783247572961PASS_SUBCRITICAL
70tp4_rho0p005e2emean0.1511028234677850.16307934217671091.197651870892591PASS_SUBCRITICAL
71tp4_rho0p005e2ep500.15942135313949180.173605270905752921.418391776626113PASS_SUBCRITICAL
72tp4_rho0p005e2ep900.12663524107184060.136521047640588560.9885806568747962PASS_SUBCRITICAL
73tp4_rho0p005e2ep990.155765376994457030.176774503437795222.100912644333819PASS_SUBCRITICAL
74tp4_rho0p01ttftmean-0.00146521439735010860.0596506200315400645.8185405634189955PASS_SUBCRITICAL
75tp4_rho0p01ttftp500.229366018814985420.241591063871249981.2225045056264565PASS_SUBCRITICAL
76tp4_rho0p01ttftp90-0.0646093465409875-0.011548419893895705-5.30609266470918PASS_SUBCRITICAL
77tp4_rho0p01ttftp99-0.09621678853313553-0.015475807392170575-8.074098114096495PASS_SUBCRITICAL
78tp4_rho0p01tpotmean0.066756090591500770.105961012632017933.9204922040517163PASS_SUBCRITICAL
79tp4_rho0p01tpotp500.084773025875512140.097037541888445271.2264516012933129PASS_SUBCRITICAL
80tp4_rho0p01tpotp900.03791832737673280.083698002017507184.577967464077439PASS_SUBCRITICAL
81tp4_rho0p01tpotp99-0.0106639547513570740.066678131605714065.601417685435699PASS_SUBCRITICAL
82tp4_rho0p01e2emean0.072129043173060960.097772880537020922.564383736395996PASS_SUBCRITICAL
83tp4_rho0p01e2ep500.120692154633076550.13883772171968321.8145567086606653PASS_SUBCRITICAL
84tp4_rho0p01e2ep900.033172939273579030.0580607605674742162.4887821293895183PASS_SUBCRITICAL
85tp4_rho0p01e2ep990.03383782711633080.063804106968934252.996627985260345PASS_SUBCRITICAL