murabcd's picture
feat: add compiled serving shared training and benchmarks
5adf069 verified
Raw History Blame Contribute Delete
360 kB
[
{
"id": "transfer-v4-0000",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3162553310394287,
"probabilities": [
0.3162553310394287,
0.12675011157989502,
0.2839660048484802,
0.27302855253219604
],
"target": 2,
"brier": 0.7033322979068473,
"nll": 1.2589007492234416
},
{
"id": "transfer-v4-0001",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9869468443068112,
"probabilities": [
0.0011030101708258786,
0.003292749480093206,
0.9869468443068112,
0.008657396042269725
],
"target": 2,
"brier": 0.0002573942103589332,
"nll": 0.013139096817765754
},
{
"id": "transfer-v4-0002",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9457581847781686,
"probabilities": [
0.9457581847781686,
0.017159962323458545,
0.016612508584791442,
0.020469344313581335
],
"target": 0,
"brier": 0.003931608323609527,
"nll": 0.05576836123399742
},
{
"id": "transfer-v4-0003",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7974075734422175,
"probabilities": [
0.7974075734422175,
0.125070110895262,
0.03682062057272062,
0.04070169508979987
],
"target": 0,
"brier": 0.05969861002046693,
"nll": 0.226389346409785
},
{
"id": "transfer-v4-0004",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9873622453566926,
"probabilities": [
0.004689515937893325,
0.005891053816673175,
0.9873622453566926,
0.0020571848887409386
],
"target": 2,
"brier": 0.00022064092689359711,
"nll": 0.012718290310632641
},
{
"id": "transfer-v4-0005",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.90338107894946,
"probabilities": [
0.90338107894946,
0.04783903647008789,
0.014167587729140037,
0.034612296851312105
],
"target": 1,
"brier": 1.7241066059094872,
"nll": 3.039913310218007
},
{
"id": "transfer-v4-0006",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8144008441418331,
"probabilities": [
0.018925906914045037,
0.14630238575579238,
0.020370863188329497,
0.8144008441418331
],
"target": 3,
"brier": 0.05662459675265754,
"nll": 0.20530259666648334
},
{
"id": "transfer-v4-0007",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.5419564762419987,
"probabilities": [
0.2646730800766784,
0.11433743515107878,
0.5419564762419987,
0.0790330085302441
],
"target": 1,
"brier": 1.1544130566700312,
"nll": 2.1686012451708763
},
{
"id": "transfer-v4-0008",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8773854927575078,
"probabilities": [
0.10740682445039598,
0.8773854927575078,
0.0028874911591911844,
0.012320191632905047
],
"target": 1,
"brier": 0.026730668051903272,
"nll": 0.1308088247410509
},
{
"id": "transfer-v4-0009",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9786612477106695,
"probabilities": [
0.0034004941671828986,
0.0023450244857730613,
0.9786612477106695,
0.015593233636374507
],
"target": 2,
"brier": 0.0007155537849238876,
"nll": 0.02156971501154877
},
{
"id": "transfer-v4-0010",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3798668086528778,
"probabilities": [
0.0867503434419632,
0.3397422730922699,
0.3798668086528778,
0.1936405748128891
],
"target": 3,
"brier": 0.917464749117411,
"nll": 1.6417515454535274
},
{
"id": "transfer-v4-0011",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.42460236560912623,
"probabilities": [
0.05030372085215221,
0.19376479496631055,
0.33132911857241104,
0.42460236560912623
],
"target": 1,
"brier": 0.9426118238621233,
"nll": 1.6411102525476007
},
{
"id": "transfer-v4-0012",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.697399094738233,
"probabilities": [
0.208275710037296,
0.011410453601219164,
0.08291474162325176,
0.697399094738233
],
"target": 3,
"brier": 0.14195113208661683,
"nll": 0.36039744279386204
},
{
"id": "transfer-v4-0013",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.43242067098617554,
"probabilities": [
0.2608932554721832,
0.08759994804859161,
0.43242067098617554,
0.21908612549304962
],
"target": 2,
"brier": 0.4458840667563293,
"nll": 0.838356389118794
},
{
"id": "transfer-v4-0014",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.510983247719081,
"probabilities": [
0.510983247719081,
0.1355653455691541,
0.24012301266651648,
0.1133283940452484
],
"target": 0,
"brier": 0.328017733039581,
"nll": 0.6714184726444263
},
{
"id": "transfer-v4-0015",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4372059735447613,
"probabilities": [
0.4372059735447613,
0.0853374085227952,
0.3873358397732365,
0.09012077815920694
],
"target": 0,
"brier": 0.4821703969359456,
"nll": 0.8273508595874551
},
{
"id": "transfer-v4-0016",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7952808378720533,
"probabilities": [
0.05452770157240932,
0.07450697048029216,
0.0756844900752452,
0.7952808378720533
],
"target": 3,
"brier": 0.05616263626923928,
"nll": 0.22905997152275506
},
{
"id": "transfer-v4-0017",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7479623706363219,
"probabilities": [
0.1062073495264441,
0.07787088585669483,
0.7479623706363219,
0.0679593939805392
],
"target": 2,
"brier": 0.0854853218030036,
"nll": 0.29040260890901437
},
{
"id": "transfer-v4-0018",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9860738727605102,
"probabilities": [
0.003726704141287443,
0.0018231748187691793,
0.9860738727605102,
0.008376248279433228
],
"target": 2,
"brier": 0.00028131084530565165,
"nll": 0.01402400552218589
},
{
"id": "transfer-v4-0019",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.364085853099823,
"probabilities": [
0.2748047709465027,
0.23245613276958466,
0.12865324318408966,
0.364085853099823
],
"target": 0,
"brier": 0.7290541393133556,
"nll": 1.2916943572617168
},
{
"id": "transfer-v4-0020",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8890133913994817,
"probabilities": [
0.0705097154237202,
0.016101577920620596,
0.8890133913994817,
0.024375315256177508
],
"target": 2,
"brier": 0.018143064063150513,
"nll": 0.11764298014019829
},
{
"id": "transfer-v4-0021",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.3013613820075989,
"probabilities": [
0.2890733480453491,
0.15473511815071106,
0.3013613820075989,
0.25483015179634094
],
"target": 2,
"brier": 0.6605406821541404,
"nll": 1.1994451297062954
},
{
"id": "transfer-v4-0022",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.470967317324497,
"probabilities": [
0.470967317324497,
0.3175520265375969,
0.16829551568297094,
0.043185140454935204
],
"target": 0,
"brier": 0.4109032058520836,
"nll": 0.7529665773425355
},
{
"id": "transfer-v4-0023",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7285483750905236,
"probabilities": [
0.7285483750905236,
0.08539792468391079,
0.02248296225380012,
0.16357073797176547
],
"target": 0,
"brier": 0.10823966011864772,
"nll": 0.31670125185826753
},
{
"id": "transfer-v4-0024",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.39541155836380193,
"probabilities": [
0.39541155836380193,
0.18113726714881634,
0.0453941644242809,
0.3780570100631008
],
"target": 3,
"brier": 0.5780347229332605,
"nll": 0.97271027446203
},
{
"id": "transfer-v4-0025",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4792089569391822,
"probabilities": [
0.4792089569391822,
0.11325704559513283,
0.23305911346657082,
0.17447488399911412
],
"target": 0,
"brier": 0.36880850442564084,
"nll": 0.7356185409132134
},
{
"id": "transfer-v4-0026",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3103709976209254,
"probabilities": [
0.22286439435790206,
0.3103709976209254,
0.20043491421185816,
0.26632969380931437
],
"target": 2,
"brier": 0.8562345266526846,
"nll": 1.6072657023323618
},
{
"id": "transfer-v4-0027",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4700322291616721,
"probabilities": [
0.02921626246368005,
0.3482405724593805,
0.4700322291616721,
0.15251093591526738
],
"target": 2,
"brier": 0.4262505100002809,
"nll": 0.7549540139446231
},
{
"id": "transfer-v4-0028",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3446461414387587,
"probabilities": [
0.3446461414387587,
0.3197187328212887,
0.20358995513275066,
0.13204517060720194
],
"target": 1,
"brier": 0.6404483621945385,
"nll": 1.140313629633622
},
{
"id": "transfer-v4-0029",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9625586103201155,
"probabilities": [
0.025382337648497122,
0.0006848235960673145,
0.011374228435320051,
0.9625586103201155
],
"target": 3,
"brier": 0.002175962781519852,
"nll": 0.03816032083507131
},
{
"id": "transfer-v4-0030",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7895772906099019,
"probabilities": [
0.10886923766007205,
0.03827291283248155,
0.7895772906099019,
0.06328055889754447
],
"target": 2,
"brier": 0.061599472526823254,
"nll": 0.23625755190221742
},
{
"id": "transfer-v4-0031",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9022671227387905,
"probabilities": [
0.9022671227387905,
0.07754311407281944,
0.009602733512115843,
0.010587029676274166
],
"target": 0,
"brier": 0.01576894752613595,
"nll": 0.10284465781854481
},
{
"id": "transfer-v4-0032",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9657904143543455,
"probabilities": [
0.006632334247641908,
0.0066567693586237755,
0.020920482039388767,
0.9657904143543455
],
"target": 3,
"brier": 0.0016962627546741119,
"nll": 0.03480843067546002
},
{
"id": "transfer-v4-0033",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9492055614612064,
"probabilities": [
0.0023789945591037144,
0.004922464407417589,
0.04349297957227227,
0.9492055614612064
],
"target": 3,
"brier": 0.004501604529499914,
"nll": 0.052129895334020064
},
{
"id": "transfer-v4-0034",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.4259699173950053,
"probabilities": [
0.16619246764724227,
0.05777069403084048,
0.4259699173950053,
0.35006692092691194
],
"target": 3,
"brier": 0.6348207671904172,
"nll": 1.0496309401272546
},
{
"id": "transfer-v4-0035",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9207886264445869,
"probabilities": [
0.9207886264445869,
0.013241070902282681,
0.05241669571361011,
0.013553606939520246
],
"target": 0,
"brier": 0.009380977909778675,
"nll": 0.0825247734702675
},
{
"id": "transfer-v4-0036",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.4215874468144949,
"probabilities": [
0.10964585340721578,
0.2279292246981537,
0.4215874468144949,
0.24083747508013564
],
"target": 0,
"brier": 1.080420902541006,
"nll": 2.2104996214569654
},
{
"id": "transfer-v4-0037",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.4866328835487366,
"probabilities": [
0.13241828978061676,
0.09311290085315704,
0.4866328835487366,
0.2878359258174896
],
"target": 3,
"brier": 0.7701938476809036,
"nll": 1.2453646632106545
},
{
"id": "transfer-v4-0038",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8851798640909811,
"probabilities": [
0.041317659745847286,
0.025317895780237083,
0.8851798640909811,
0.04818458038293451
],
"target": 2,
"brier": 0.017853562250457592,
"nll": 0.12196441836290298
},
{
"id": "transfer-v4-0039",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.48867644062786125,
"probabilities": [
0.48867644062786125,
0.41949395361062397,
0.07520955238067392,
0.01662005338084082
],
"target": 0,
"brier": 0.4433596624285488,
"nll": 0.7160546841188273
},
{
"id": "transfer-v4-0040",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.6525671579326265,
"probabilities": [
0.07325777520623468,
0.18739781062897756,
0.08677725623216116,
0.6525671579326265
],
"target": 3,
"brier": 0.16872451300289595,
"nll": 0.42684122104692696
},
{
"id": "transfer-v4-0041",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.53332892258985,
"probabilities": [
0.12312377347151626,
0.04613990096018235,
0.2974074029784514,
0.53332892258985
],
"target": 3,
"brier": 0.3235214118920179,
"nll": 0.6286169296006032
},
{
"id": "transfer-v4-0042",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4374687811392327,
"probabilities": [
0.4374687811392327,
0.1338954726268603,
0.2645471416141094,
0.16408860461979757
],
"target": 0,
"brier": 0.4312796300852187,
"nll": 0.8267499331265675
},
{
"id": "transfer-v4-0043",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8080322772563706,
"probabilities": [
0.07718183874034076,
0.8080322772563706,
0.04470274986588489,
0.07008313413740372
],
"target": 1,
"brier": 0.049718624342808125,
"nll": 0.21315327415943722
},
{
"id": "transfer-v4-0044",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9973433881956151,
"probabilities": [
0.0017805689227665168,
0.00016590325603989,
0.000710139625578466,
0.9973433881956151
],
"target": 3,
"brier": 1.0759834146100591e-05,
"nll": 0.0026601468597590994
},
{
"id": "transfer-v4-0045",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8921799987678231,
"probabilities": [
0.060027772334508296,
0.010595156716279407,
0.8921799987678231,
0.03719707218138919
],
"target": 2,
"brier": 0.016724365641860195,
"nll": 0.11408737441885464
},
{
"id": "transfer-v4-0046",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9807024429151833,
"probabilities": [
0.9807024429151833,
0.005766191886109719,
0.009495843969589924,
0.004035521229117044
],
"target": 0,
"brier": 0.0005121011625946496,
"nll": 0.01948618559564928
},
{
"id": "transfer-v4-0047",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.6938598648628612,
"probabilities": [
0.0555797956052453,
0.09618544435224766,
0.6938598648628612,
0.15437489517964578
],
"target": 2,
"brier": 0.1298941439882724,
"nll": 0.36548526269342385
},
{
"id": "transfer-v4-0048",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.4964281731684441,
"probabilities": [
0.19503083098564927,
0.4964281731684441,
0.07735473374445984,
0.23118626210144677
],
"target": 3,
"brier": 0.8815362745645332,
"nll": 1.4645315639257928
},
{
"id": "transfer-v4-0049",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7496233158358976,
"probabilities": [
0.031273886039971804,
0.20077935427960844,
0.018323443844522183,
0.7496233158358976
],
"target": 3,
"brier": 0.1043146376203117,
"nll": 0.2881844441714613
},
{
"id": "transfer-v4-0050",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8209808312076078,
"probabilities": [
0.8209808312076078,
0.17644212803145534,
0.0008941828102518361,
0.0016828579506849982
],
"target": 0,
"brier": 0.06318331891316784,
"nll": 0.197255517905072
},
{
"id": "transfer-v4-0051",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.6675016905648345,
"probabilities": [
0.08487124786444454,
0.03196308686985512,
0.6675016905648345,
0.21566397470086576
],
"target": 3,
"brier": 1.0689662751252742,
"nll": 1.5340337552943308
},
{
"id": "transfer-v4-0052",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9371446530732953,
"probabilities": [
0.9371446530732953,
0.02171118456352574,
0.011140824708117884,
0.030003337655061035
],
"target": 0,
"brier": 0.005446488418048497,
"nll": 0.06491762971196484
},
{
"id": "transfer-v4-0053",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.5200689473753344,
"probabilities": [
0.2790358683395078,
0.0995523713495759,
0.1013428129355819,
0.5200689473753344
],
"target": 3,
"brier": 0.3283758714684229,
"nll": 0.6537938850896756
},
{
"id": "transfer-v4-0054",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.25945952921300425,
"probabilities": [
0.25382116815181327,
0.23876911757542368,
0.25945952921300425,
0.2479501850597588
],
"target": 2,
"brier": 0.7313153600542915,
"nll": 1.3491545453286828
},
{
"id": "transfer-v4-0055",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.3181339705546507,
"probabilities": [
0.25490166977340967,
0.20348429073440163,
0.3181339705546507,
0.223480068937538
],
"target": 2,
"brier": 0.6212653411528477,
"nll": 1.1452826938677583
},
{
"id": "transfer-v4-0056",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.427986049235075,
"probabilities": [
0.1700955753014151,
0.21137439889647963,
0.19054397656703032,
0.427986049235075
],
"target": 3,
"brier": 0.43711860812164255,
"nll": 0.8486646791767287
},
{
"id": "transfer-v4-0057",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3176527822717195,
"probabilities": [
0.19665721962877453,
0.27249144695724703,
0.2131985511422589,
0.3176527822717195
],
"target": 2,
"brier": 0.8328854607065792,
"nll": 1.5455313824815553
},
{
"id": "transfer-v4-0058",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4638698364505929,
"probabilities": [
0.21051794133694512,
0.21551112670070582,
0.4638698364505929,
0.11010109551175612
],
"target": 2,
"brier": 0.39032065285695605,
"nll": 0.7681512910013127
},
{
"id": "transfer-v4-0059",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9413983462403228,
"probabilities": [
0.9413983462403228,
0.023227487735145727,
0.010841919626557544,
0.024532246397973873
],
"target": 0,
"brier": 0.004693048344375068,
"nll": 0.060388906719078324
},
{
"id": "transfer-v4-0060",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.47708170717429915,
"probabilities": [
0.47708170717429915,
0.0404313422659162,
0.05199855096640902,
0.43048839959337565
],
"target": 0,
"brier": 0.4631023458962411,
"nll": 0.7400675088964598
},
{
"id": "transfer-v4-0061",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.30474344122963726,
"probabilities": [
0.30474344122963726,
0.28393760535074475,
0.11915057241283783,
0.2921683810067801
],
"target": 1,
"brier": 0.7051731397697372,
"nll": 1.2590007644276033
},
{
"id": "transfer-v4-0062",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8522660199721606,
"probabilities": [
0.08441097352214882,
0.04293287949959099,
0.020390127006099573,
0.8522660199721606
],
"target": 3,
"brier": 0.031209530727274244,
"nll": 0.15985657087219546
},
{
"id": "transfer-v4-0063",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.3845955018819719,
"probabilities": [
0.1338500191614026,
0.3845955018819719,
0.22883308741947747,
0.252721391537148
],
"target": 1,
"brier": 0.5128712075718126,
"nll": 0.9555631414705476
},
{
"id": "transfer-v4-0064",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9724321356299965,
"probabilities": [
0.007500186555553054,
0.008312683544761796,
0.9724321356299965,
0.01175499426968862
],
"target": 2,
"brier": 0.0010235205422867715,
"nll": 0.027954989338396716
},
{
"id": "transfer-v4-0065",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4166145158604659,
"probabilities": [
0.2000198725617264,
0.35682503518839476,
0.026540576389412953,
0.4166145158604659
],
"target": 3,
"brier": 0.5083750804566093,
"nll": 0.8755939071221904
},
{
"id": "transfer-v4-0066",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.5159400816844422,
"probabilities": [
0.3103888998267554,
0.08883319248631281,
0.08483782600248961,
0.5159400816844422
],
"target": 0,
"brier": 0.7568464301788406,
"nll": 1.1699292521799203
},
{
"id": "transfer-v4-0067",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.2576332986354828,
"probabilities": [
0.24747757613658905,
0.2576332986354828,
0.24141107499599457,
0.2534780502319336
],
"target": 3,
"brier": 0.7431943958724783,
"nll": 1.3724780465560351
},
{
"id": "transfer-v4-0068",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3733322544891986,
"probabilities": [
0.06859289518552394,
0.30899496728151843,
0.3733322544891986,
0.24907988304375905
],
"target": 1,
"brier": 0.6836107008912825,
"nll": 1.1744302893318552
},
{
"id": "transfer-v4-0069",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.4953980482771847,
"probabilities": [
0.4953980482771847,
0.2666862626871933,
0.1828048689872389,
0.055110820048383025
],
"target": 1,
"brier": 0.8196230861803666,
"nll": 1.3216823576052406
},
{
"id": "transfer-v4-0070",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.4714620026109518,
"probabilities": [
0.10724398228126684,
0.31537426927868734,
0.4714620026109518,
0.10591974582909401
],
"target": 2,
"brier": 0.4015336086991361,
"nll": 0.7519167684679106
},
{
"id": "transfer-v4-0071",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9534453733007715,
"probabilities": [
0.0028821047223346425,
0.04237154276010857,
0.0013009792167852855,
0.9534453733007715
],
"target": 3,
"brier": 0.003972679977529239,
"nll": 0.047673146300435884
},
{
"id": "transfer-v4-0072",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.8067489335288113,
"probabilities": [
0.17621597609958972,
0.011191071002194457,
0.8067489335288113,
0.005844019369404497
],
"target": 0,
"brier": 1.3296233524159922,
"nll": 1.7360448993316189
},
{
"id": "transfer-v4-0073",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9760753614025042,
"probabilities": [
0.0014589627850571589,
0.010271230515387787,
0.9760753614025042,
0.01219444529705092
],
"target": 2,
"brier": 0.0008287195768319695,
"nll": 0.024215480998188543
},
{
"id": "transfer-v4-0074",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.677931630761737,
"probabilities": [
0.2266967525840519,
0.009591656145158162,
0.677931630761737,
0.08577996050905297
],
"target": 2,
"brier": 0.16256965358849057,
"nll": 0.3887088357108529
},
{
"id": "transfer-v4-0075",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9462885746465929,
"probabilities": [
0.03373535683221001,
0.006582110577936859,
0.9462885746465929,
0.013393957943260228
],
"target": 2,
"brier": 0.004245713803137176,
"nll": 0.055207709252564734
},
{
"id": "transfer-v4-0076",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.6694853006533399,
"probabilities": [
0.23597795206406927,
0.6694853006533399,
0.04828697599677849,
0.04624977128581235
],
"target": 1,
"brier": 0.16939623373946872,
"nll": 0.40124606980017014
},
{
"id": "transfer-v4-0077",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.5402671815514679,
"probabilities": [
0.050441057617389956,
0.5402671815514679,
0.3252416921833536,
0.08405006864778851
],
"target": 2,
"brier": 0.7567961157624097,
"nll": 1.1231867047801478
},
{
"id": "transfer-v4-0078",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9387789606210427,
"probabilities": [
0.0054624236897012485,
0.04622311713625882,
0.9387789606210427,
0.009535498552997186
],
"target": 2,
"brier": 0.0060053560256521634,
"nll": 0.06317522618413185
},
{
"id": "transfer-v4-0079",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.43283125435686665,
"probabilities": [
0.06211865647048759,
0.43283125435686665,
0.1184016457319137,
0.386648443440732
],
"target": 3,
"brier": 0.5814207038755396,
"nll": 0.9502394136930338
},
{
"id": "transfer-v4-0080",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5533168881014908,
"probabilities": [
0.06384582781877837,
0.18654067710112401,
0.5533168881014908,
0.028856402101797598,
0.03701861182031066,
0.1304215930564985
],
"target": 1,
"brier": 0.991164799898039,
"nll": 1.679105955899485
},
{
"id": "transfer-v4-0081",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5285747006934394,
"probabilities": [
0.21017056527404573,
0.016869287796482824,
0.013835762511452788,
0.5285747006934394,
0.06700146887170783,
0.16354821485287144
],
"target": 0,
"brier": 0.9349349667802407,
"nll": 1.5598358623425614
},
{
"id": "transfer-v4-0082",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8300547407496612,
"probabilities": [
0.8300547407496612,
0.0024209243150237086,
0.00191705029207596,
0.04910913741068002,
0.09884058455130128,
0.017657562681257843
],
"target": 0,
"brier": 0.04138388514953281,
"nll": 0.18626362765584262
},
{
"id": "transfer-v4-0083",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.6777951500077816,
"probabilities": [
0.21017025095430675,
0.09104991467948526,
0.6777951500077816,
0.006276038826035643,
0.008028957510122517,
0.006679688022268267
],
"target": 0,
"brier": 1.0916758558689155,
"nll": 1.5598373578896358
},
{
"id": "transfer-v4-0084",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9619174164597741,
"probabilities": [
0.001273295318862047,
0.9619174164597741,
0.029031314505419497,
0.0008145050010137268,
0.00095534547335099,
0.00600812324157964
],
"target": 1,
"brier": 0.0023323953202360366,
"nll": 0.038826677677291956
},
{
"id": "transfer-v4-0085",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.34893673008425663,
"probabilities": [
0.22670857186040708,
0.26024457327565975,
0.06856473407587532,
0.34893673008425663,
0.04406690887982195,
0.05147848182397929
],
"target": 0,
"brier": 0.7967567616635146,
"nll": 1.484089910712792
},
{
"id": "transfer-v4-0086",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5462894528732313,
"probabilities": [
0.0052693468446038385,
0.38561741146101125,
0.5462894528732313,
0.006362286500018102,
0.006672672570470506,
0.049788829750665016
],
"target": 1,
"brier": 0.6784898282532532,
"nll": 0.9529095630612995
},
{
"id": "transfer-v4-0087",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9052892132796336,
"probabilities": [
0.9052892132796336,
0.002385466232530614,
0.0008815970895682102,
0.05701508625908148,
0.021689129092679147,
0.01273950804650697
],
"target": 0,
"brier": 0.012860034230962023,
"nll": 0.09950081365000692
},
{
"id": "transfer-v4-0088",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7180075846962188,
"probabilities": [
0.018263884747802092,
0.7180075846962188,
0.21935527311455355,
0.004786825941481878,
0.006053493491228562,
0.03353293800871508
],
"target": 1,
"brier": 0.1291540440356403,
"nll": 0.33127514634594896
},
{
"id": "transfer-v4-0089",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5512874149538515,
"probabilities": [
0.5512874149538515,
0.006961426261185126,
0.006717246985274937,
0.12546132557520268,
0.12314755521171167,
0.1864250310127741
],
"target": 0,
"brier": 0.26709672359927056,
"nll": 0.5954989815921877
},
{
"id": "transfer-v4-0090",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7327793354252827,
"probabilities": [
0.7327793354252827,
0.006889607493317853,
0.003820781966076535,
0.1425086546883919,
0.07893662919235363,
0.03506499123457734
],
"target": 0,
"brier": 0.09923821034162528,
"nll": 0.31091066549406127
},
{
"id": "transfer-v4-0091",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8136086702613841,
"probabilities": [
0.008584090760349165,
0.8136086702613841,
0.09898852102285104,
0.007526364863925141,
0.009827602011681966,
0.0614647510798086
],
"target": 1,
"brier": 0.048545285264870564,
"nll": 0.2062757776411173
},
{
"id": "transfer-v4-0092",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.7223941437569404,
"probabilities": [
0.10482480139554448,
0.08754776097134088,
0.7223941437569404,
0.036510234604153965,
0.02448346398131934,
0.024239595290700862
],
"target": 1,
"brier": 1.3679306216495837,
"nll": 2.435570794862388
},
{
"id": "transfer-v4-0093",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4305843300592515,
"probabilities": [
0.21931841397572718,
0.17565866846736267,
0.059035046349297,
0.012223664352425745,
0.10317987679593586,
0.4305843300592515
],
"target": 4,
"brier": 1.0722802878605469,
"nll": 2.2712814372355856
},
{
"id": "transfer-v4-0094",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7728466089260229,
"probabilities": [
0.11853847934062021,
0.06005619603920706,
0.7728466089260229,
0.014405317041069907,
0.018230264293336216,
0.01592313435974378
],
"target": 2,
"brier": 0.0700501827465906,
"nll": 0.25767468614523376
},
{
"id": "transfer-v4-0095",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.49632723864542017,
"probabilities": [
0.0006048276620755582,
0.48812912709561057,
0.49632723864542017,
0.0008401165115873558,
0.0008681439053791712,
0.013230546179927147
],
"target": 2,
"brier": 0.4921331678879838,
"nll": 0.7005198144665731
},
{
"id": "transfer-v4-0096",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8139624723544494,
"probabilities": [
0.8139624723544494,
0.004125281138312396,
0.04456098028977738,
0.07511863035506494,
0.03551715555776689,
0.026715480304628954
],
"target": 3,
"brier": 1.5219183384533364,
"nll": 2.5886866770083996
},
{
"id": "transfer-v4-0097",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.7448300525547407,
"probabilities": [
0.7448300525547407,
0.006341167136829061,
0.015567655584704153,
0.1256776817974686,
0.06909273192973664,
0.038490710996520926
],
"target": 3,
"brier": 1.3257492260353396,
"nll": 2.074034730482827
},
{
"id": "transfer-v4-0098",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8371038042568237,
"probabilities": [
0.8371038042568237,
0.0009124331628989503,
0.001014598204058342,
0.054450222671869684,
0.08490260895048735,
0.02161633275386189
],
"target": 4,
"brier": 1.5415799687414056,
"nll": 2.4662504564492638
},
{
"id": "transfer-v4-0099",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8645880143812549,
"probabilities": [
0.8645880143812549,
0.0038478863076149565,
0.002591670700098584,
0.050966117068268695,
0.060036081275575054,
0.017970230267187817
],
"target": 0,
"brier": 0.024882734155064992,
"nll": 0.14550216946179315
},
{
"id": "transfer-v4-0100",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5065839794665691,
"probabilities": [
0.5065839794665691,
0.0017845354417353485,
0.0010634410234753974,
0.4287325065952876,
0.04616882940727084,
0.01566670806566178
],
"target": 0,
"brier": 0.42965225355453107,
"nll": 0.6800651655494813
},
{
"id": "transfer-v4-0101",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7940659847479733,
"probabilities": [
0.0013344083526611015,
0.7940659847479733,
0.016452471466597344,
0.0015793565607576344,
0.0038558274220437073,
0.18271195144996688
],
"target": 1,
"brier": 0.07608230207574247,
"nll": 0.23058871697137437
},
{
"id": "transfer-v4-0102",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.3861285042168059,
"probabilities": [
0.08851144215525755,
0.0984601350931413,
0.3861285042168059,
0.016441044869617238,
0.3731573417831955,
0.0373015318819825
],
"target": 4,
"brier": 0.5612173257611279,
"nll": 0.9857551204456864
},
{
"id": "transfer-v4-0103",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.6209330524079517,
"probabilities": [
0.016524324101259983,
0.2839446051943417,
0.6209330524079517,
0.02167655515478986,
0.027663433769735877,
0.029258029371920808
],
"target": 0,
"brier": 1.4354979703701494,
"nll": 4.102921795668778
},
{
"id": "transfer-v4-0104",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.3204523825510626,
"probabilities": [
0.3204523825510626,
0.10151926870586667,
0.05378442842410718,
0.14195882851008093,
0.12318496038958548,
0.2591001314192971
],
"target": 3,
"brier": 0.9344307206816079,
"nll": 1.9522182034914775
},
{
"id": "transfer-v4-0105",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5550315747408688,
"probabilities": [
0.0030836808621390924,
0.5550315747408688,
0.41467611272873545,
0.00229964349255038,
0.00337121388951669,
0.02153777428618957
],
"target": 2,
"brier": 0.6511541402218167,
"nll": 0.880257514718131
},
{
"id": "transfer-v4-0106",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9335495112901558,
"probabilities": [
0.9335495112901558,
0.001306249393965853,
0.001538685735921129,
0.014716869029964733,
0.016048060522725022,
0.032840624027267416
],
"target": 0,
"brier": 0.005972374358136804,
"nll": 0.0687612790670936
},
{
"id": "transfer-v4-0107",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.3903874747743811,
"probabilities": [
0.3903874747743811,
0.20710462384705422,
0.13835843938279446,
0.07859777499718777,
0.11352487754262071,
0.0720268094559617
],
"target": 0,
"brier": 0.45791618321520894,
"nll": 0.9406155080152974
},
{
"id": "transfer-v4-0108",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8645158520779507,
"probabilities": [
0.0031032942167206626,
0.8645158520779507,
0.023840509660362275,
0.005976544303984832,
0.00678100445609429,
0.09578279528488726
],
"target": 1,
"brier": 0.028189999649862785,
"nll": 0.14558563732598093
},
{
"id": "transfer-v4-0109",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7612104095787559,
"probabilities": [
0.7612104095787559,
0.007962313461456965,
0.00488724708662498,
0.0516857713063712,
0.10391463039582552,
0.07033962817096549
],
"target": 0,
"brier": 0.07552508477035497,
"nll": 0.2728454684319505
},
{
"id": "transfer-v4-0110",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8368847762858543,
"probabilities": [
0.0007727973705529884,
0.8368847762858543,
0.13777098233798857,
0.0009713324488864427,
0.0019234447299751453,
0.02167666682674257
],
"target": 1,
"brier": 0.04606253800853921,
"nll": 0.17806888070996132
},
{
"id": "transfer-v4-0111",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.582172211731753,
"probabilities": [
0.29881027173915725,
0.003124227729863146,
0.0019997507222010713,
0.582172211731753,
0.08982881108394557,
0.02406472699307989
],
"target": 0,
"brier": 0.8392536053190213,
"nll": 1.2079464496772654
},
{
"id": "transfer-v4-0112",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.375675490629421,
"probabilities": [
0.2977839278681536,
0.375675490629421,
0.2708210500416001,
0.01667075697355477,
0.016146100097117953,
0.02290267439015253
],
"target": 0,
"brier": 0.7086466705462084,
"nll": 1.2113871297381547
},
{
"id": "transfer-v4-0113",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6539960986944587,
"probabilities": [
0.6539960986944587,
0.011115643004291322,
0.0038126776269315405,
0.05556681656466228,
0.16386192754707704,
0.11164683656257905
],
"target": 0,
"brier": 0.16226021226574608,
"nll": 0.42465389284172356
},
{
"id": "transfer-v4-0114",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4709452776414394,
"probabilities": [
0.042296503527024826,
0.4709452776414394,
0.33195827029567715,
0.02297195462457751,
0.055204850718469374,
0.07662314319281174
],
"target": 2,
"brier": 0.6793045936845958,
"nll": 1.1027460098460253
},
{
"id": "transfer-v4-0115",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9177495251606481,
"probabilities": [
0.031394708584697485,
0.9177495251606481,
0.026532121311811943,
0.0027437872445875903,
0.0033633618476011087,
0.018216495850653807
],
"target": 1,
"brier": 0.008805403092159988,
"nll": 0.08583077400042598
},
{
"id": "transfer-v4-0116",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8155117245345466,
"probabilities": [
0.8155117245345466,
0.0029955197710814603,
0.07233975701973439,
0.009609506240087858,
0.0566467760860959,
0.04289671634845381
],
"target": 1,
"brier": 1.6694516750201267,
"nll": 5.810637516201198
},
{
"id": "transfer-v4-0117",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6846204057463082,
"probabilities": [
0.01176806396598047,
0.6846204057463082,
0.269416491230303,
0.0039080056877278035,
0.003412043103602448,
0.026874990266078026
],
"target": 1,
"brier": 0.17293720119637654,
"nll": 0.3788907465141574
},
{
"id": "transfer-v4-0118",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6514582285109459,
"probabilities": [
0.6514582285109459,
0.023408979786544725,
0.004510387071084924,
0.1286790004008985,
0.10538688482740347,
0.08655651940312249
],
"target": 0,
"brier": 0.15720640208788783,
"nll": 0.42854200034236234
},
{
"id": "transfer-v4-0119",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8994137168860741,
"probabilities": [
0.8994137168860741,
0.007599883852331032,
0.024480609309945344,
0.02406116952861659,
0.03036668579685654,
0.014077934626176404
],
"target": 0,
"brier": 0.012473922546138697,
"nll": 0.10601215360986628
},
{
"id": "transfer-v4-0120",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6271285537348126,
"probabilities": [
0.6271285537348126,
0.0020720726284324427,
0.020101700371257688,
0.026390068749144156,
0.29624260051277895,
0.02806500400357422
],
"target": 0,
"brier": 0.228685245819565,
"nll": 0.4666037294848858
},
{
"id": "transfer-v4-0121",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.479497627927988,
"probabilities": [
0.0029116330320490607,
0.45294873641015765,
0.479497627927988,
0.0049219232540040295,
0.0026695250253325788,
0.05705055435046867
],
"target": 1,
"brier": 0.5324776552347987,
"nll": 0.7919763245601946
},
{
"id": "transfer-v4-0122",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5198550000383577,
"probabilities": [
0.5198550000383577,
0.002542685374990852,
0.002651268967780108,
0.09419903498449794,
0.342981174715907,
0.03777083591846641
],
"target": 2,
"brier": 1.3928963580528702,
"nll": 5.932716897832762
},
{
"id": "transfer-v4-0123",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5130647994830043,
"probabilities": [
0.00039801857029941315,
0.5130647994830043,
0.4700283387919133,
0.0012937394147892066,
0.0006136617713252216,
0.01460144196866856
],
"target": 1,
"brier": 0.45824793963880206,
"nll": 0.667353127006723
},
{
"id": "transfer-v4-0124",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5850087643977121,
"probabilities": [
0.013495196210023605,
0.5850087643977121,
0.2652068246799524,
0.018278420720482722,
0.020647936415401476,
0.09736285757642774
],
"target": 1,
"brier": 0.25297446978198085,
"nll": 0.5361284499860768
},
{
"id": "transfer-v4-0125",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6654467619428688,
"probabilities": [
0.002992479111932926,
0.6654467619428688,
0.29275349302123976,
0.010070620189538717,
0.008220317082587986,
0.0205163286518318
],
"target": 1,
"brier": 0.19822934244717416,
"nll": 0.4072966414274957
},
{
"id": "transfer-v4-0126",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5445003362460903,
"probabilities": [
0.05632013302921889,
0.378927876251835,
0.5445003362460903,
0.005016723977881488,
0.00593367249511508,
0.009301257999859302
],
"target": 2,
"brier": 0.35438512585420917,
"nll": 0.6078867190774663
},
{
"id": "transfer-v4-0127",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.884683266596579,
"probabilities": [
0.884683266596579,
0.001271364098885338,
0.023152225420506538,
0.05194060616353512,
0.014183551292737177,
0.024768986427756823
],
"target": 0,
"brier": 0.01734809329599712,
"nll": 0.12252558888374575
},
{
"id": "transfer-v4-0128",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5282927064472669,
"probabilities": [
0.5282927064472669,
0.004661014688919511,
0.0023093111415186376,
0.06376626232669144,
0.1767153113435644,
0.2242553940520391
],
"target": 1,
"brier": 1.3553831315192224,
"nll": 5.368522110144126
},
{
"id": "transfer-v4-0129",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9482382835309209,
"probabilities": [
0.015755377216933104,
0.0005446497064113374,
0.0004870224649916301,
0.9482382835309209,
0.012258236844278738,
0.022716430236464292
],
"target": 3,
"brier": 0.003594341610475874,
"nll": 0.05314945437565275
},
{
"id": "transfer-v4-0130",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5337883144540808,
"probabilities": [
0.5337883144540808,
0.0027930559122236387,
0.0010367678304558424,
0.36539938433357616,
0.06419818740750907,
0.032784290062154435
],
"target": 0,
"brier": 0.3560751388010758,
"nll": 0.6277559334950903
},
{
"id": "transfer-v4-0131",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.939076788621174,
"probabilities": [
0.002132058956296628,
0.939076788621174,
0.02065850679357929,
0.002940659480444711,
0.002453429022252202,
0.03273855712625311
],
"target": 1,
"brier": 0.0052294371778986905,
"nll": 0.06285802609807763
},
{
"id": "transfer-v4-0132",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8288192044191177,
"probabilities": [
0.0016291991135507766,
0.8288192044191177,
0.07292661499557325,
0.0018175834461440846,
0.00622819260987887,
0.08857920541573534
],
"target": 1,
"brier": 0.042512179865020455,
"nll": 0.18775323639025707
},
{
"id": "transfer-v4-0133",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8729020311861416,
"probabilities": [
0.8729020311861416,
0.0019230673837362,
0.0017027842024002501,
0.05435771465556246,
0.02739139074065417,
0.04172301183150527
],
"target": 0,
"brier": 0.02160635048438552,
"nll": 0.13593195030329328
},
{
"id": "transfer-v4-0134",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7091492198178201,
"probabilities": [
0.007533682280473323,
0.7091492198178201,
0.2421334759054041,
0.00473688807791743,
0.003364607356310924,
0.033082126562074154
],
"target": 1,
"brier": 0.14440773864451273,
"nll": 0.34368930940736564
},
{
"id": "transfer-v4-0135",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4680312343449184,
"probabilities": [
0.4680312343449184,
0.008834848307948699,
0.0062211813371892185,
0.21320781419493362,
0.1589669757187256,
0.14473794609628446
],
"target": 4,
"brier": 0.9929131869699417,
"nll": 1.8390587982167421
},
{
"id": "transfer-v4-0136",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5210462978450772,
"probabilities": [
0.012715851371227575,
0.33290408146720646,
0.5210462978450772,
0.02302434556731218,
0.018715529381338067,
0.09159389436783856
],
"target": 1,
"brier": 0.7259377349115611,
"nll": 1.0999008741362537
},
{
"id": "transfer-v4-0137",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.7707513046520884,
"probabilities": [
0.008053589687250458,
0.7707513046520884,
0.042593505630209166,
0.009261363272195339,
0.01321431727348191,
0.15612591948477475
],
"target": 5,
"brier": 1.3083204954476984,
"nll": 1.8570924211396482
},
{
"id": "transfer-v4-0138",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5611289802319815,
"probabilities": [
0.5611289802319815,
0.1095675316777177,
0.04515754109424585,
0.10121216738088616,
0.110147082546507,
0.0727866970686618
],
"target": 1,
"brier": 1.137449102505983,
"nll": 2.2112141921735335
},
{
"id": "transfer-v4-0139",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4420870906425579,
"probabilities": [
0.04405163666682894,
0.4420870906425579,
0.22720304470066793,
0.06961519374870052,
0.0170521775938895,
0.19999085664735522
],
"target": 2,
"brier": 0.839730071229651,
"nll": 1.4819111912536833
},
{
"id": "transfer-v4-0140",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5130070760864425,
"probabilities": [
0.0024505810910026185,
0.5130070760864425,
0.4610676450654219,
0.0021169838855624613,
0.0017152720711662627,
0.01964244180040428
],
"target": 1,
"brier": 0.45014473591466564,
"nll": 0.667465640365674
},
{
"id": "transfer-v4-0141",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.570297891550717,
"probabilities": [
0.06272570730442453,
0.570297891550717,
0.048446245040313855,
0.016776563443461772,
0.17216715056293505,
0.12958644209814776
],
"target": 4,
"brier": 1.033902563786259,
"nll": 1.7592894684675815
},
{
"id": "transfer-v4-0142",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5227770970896085,
"probabilities": [
0.0099145614887542,
0.5227770970896085,
0.4282695190619339,
0.007327999220371221,
0.004677282794404416,
0.027033540344927807
],
"target": 2,
"brier": 0.6010763234551181,
"nll": 0.8480025641547413
},
{
"id": "transfer-v4-0143",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8100312054262516,
"probabilities": [
0.019598306787759666,
0.8100312054262516,
0.04570683332508453,
0.005698900506533953,
0.020478505243823983,
0.0984862487105462
],
"target": 0,
"brier": 1.6295785362594213,
"nll": 3.9323121048569654
},
{
"id": "transfer-v4-0144",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6344239074355296,
"probabilities": [
0.013246433723042685,
0.6344239074355296,
0.10752516169783088,
0.03536589793156713,
0.01423417860675673,
0.19520442060527304
],
"target": 1,
"brier": 0.18494113226018533,
"nll": 0.45503792425881334
},
{
"id": "transfer-v4-0145",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.751550838793655,
"probabilities": [
0.0013711501038066872,
0.751550838793655,
0.16415705772873967,
0.0017325342509415553,
0.0023114272850445097,
0.07887699183781256
],
"target": 1,
"brier": 0.09490632957130742,
"nll": 0.28561642231856027
},
{
"id": "transfer-v4-0146",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9600956238853751,
"probabilities": [
0.9600956238853751,
0.0011848961612008204,
0.000665893972614217,
0.022719771098322857,
0.011659655890688176,
0.0036741589917988534
],
"target": 0,
"brier": 0.0022598416453395043,
"nll": 0.04072239126689151
},
{
"id": "transfer-v4-0147",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.23976447224090558,
"probabilities": [
0.23976447224090558,
0.21221083876961855,
0.19055608340850658,
0.07882412699216888,
0.14695445031570906,
0.13169002827309134
],
"target": 2,
"brier": 0.8028710133574789,
"nll": 1.6578087266483574
},
{
"id": "transfer-v4-0148",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.3068494292154738,
"probabilities": [
0.3068494292154738,
0.13662091304722168,
0.20452994717746817,
0.1203235796190375,
0.13408577841775948,
0.09759035252303935
],
"target": 2,
"brier": 0.7875750877210066,
"nll": 1.5870408732550976
},
{
"id": "transfer-v4-0149",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.48885589974612714,
"probabilities": [
0.48885589974612714,
0.005961637494978414,
0.005963434947552444,
0.40859395379739055,
0.05439247206149382,
0.03623260195245762
],
"target": 3,
"brier": 0.5930836483407993,
"nll": 0.8950333940713119
},
{
"id": "transfer-v4-0150",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9019198728117387,
"probabilities": [
0.0382099959076011,
0.005555549460566899,
0.0013738227573130523,
0.04414041200580633,
0.008800347056973912,
0.9019198728117387
],
"target": 5,
"brier": 0.013138288735667246,
"nll": 0.10322959566833098
},
{
"id": "transfer-v4-0151",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6172553352595288,
"probabilities": [
0.28321287273328366,
0.007665287767525381,
0.00684611039386596,
0.02205912787330537,
0.6172553352595288,
0.06296126597249078
],
"target": 4,
"brier": 0.23125936166860836,
"nll": 0.48247250719836937
},
{
"id": "transfer-v4-0152",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8302871451504032,
"probabilities": [
0.8302871451504032,
0.0018068535428790156,
0.004092762180976432,
0.0702076394007711,
0.08025307824428603,
0.013352521480684172
],
"target": 3,
"brier": 1.5605294390502642,
"nll": 2.656298150498398
},
{
"id": "transfer-v4-0153",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.73202435700896,
"probabilities": [
0.0007046939431625638,
0.73202435700896,
0.23098067478123288,
0.0008007392593046205,
0.0009064029837669675,
0.03458313202357302
],
"target": 1,
"brier": 0.1263609697226988,
"nll": 0.31194149097200846
},
{
"id": "transfer-v4-0154",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.420801575231646,
"probabilities": [
0.21707580787395286,
0.13949669238905266,
0.11458756712600988,
0.05796496543079409,
0.0500733919485445,
0.420801575231646
],
"target": 1,
"brier": 0.9836594068294283,
"nll": 1.9697143884745552
},
{
"id": "transfer-v4-0155",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.8530523457731668,
"probabilities": [
0.8530523457731668,
0.0011565457829472762,
0.0005705710869004712,
0.11147949427358604,
0.02628285339452124,
0.007458189688878136
],
"target": 3,
"brier": 1.5179150698509314,
"nll": 2.193914612855303
},
{
"id": "transfer-v4-0156",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8372011196387947,
"probabilities": [
0.0016715127299607444,
0.8372011196387947,
0.11067572251522316,
0.0018619973005661703,
0.0021287361189658792,
0.04646091169648931
],
"target": 1,
"brier": 0.0409219998230156,
"nll": 0.17769095104998894
},
{
"id": "transfer-v4-0157",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7185327780894178,
"probabilities": [
0.7185327780894178,
0.0025177520374077083,
0.11102646240299278,
0.02930010390572389,
0.12318750083672055,
0.01543540272773724
],
"target": 0,
"brier": 0.10782891954775661,
"nll": 0.3305439543374212
},
{
"id": "transfer-v4-0158",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.6116210760617038,
"probabilities": [
0.6116210760617038,
0.003595023382082943,
0.0018083258594299672,
0.24196316073660087,
0.1110246692559451,
0.029987744704237287
],
"target": 3,
"brier": 0.961942126614691,
"nll": 1.418969792774517
},
{
"id": "transfer-v4-0159",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.42869740084967123,
"probabilities": [
0.12171433040453365,
0.0023112468286388046,
0.0013668455231295143,
0.3856017800102982,
0.06030839638372859,
0.42869740084967123
],
"target": 5,
"brier": 0.49353408357181955,
"nll": 0.8470039682618258
},
{
"id": "transfer-v4-0160",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5947177410125732,
"probabilities": [
0.40528225898742676,
0.5947177410125732
],
"target": 1,
"brier": 0.3285074188999033,
"nll": 0.5196683708454177
},
{
"id": "transfer-v4-0161",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5040452480316162,
"probabilities": [
0.5040452480316162,
0.4959547519683838
],
"target": 1,
"brier": 0.508123224126507,
"nll": 0.7012705822887363
},
{
"id": "transfer-v4-0162",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9507546722888947,
"probabilities": [
0.9507546722888947,
0.04924532771110535
],
"target": 0,
"brier": 0.00485020460274832,
"nll": 0.05049921786673238
},
{
"id": "transfer-v4-0163",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7662073820829391,
"probabilities": [
0.7662073820829391,
0.23379261791706085
],
"target": 0,
"brier": 0.1093179763850256,
"nll": 0.2663024120935871
},
{
"id": "transfer-v4-0164",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.7381079196929932,
"probabilities": [
0.7381079196929932,
0.26189208030700684
],
"target": 1,
"brier": 1.089606602227036,
"nll": 1.339822767303289
},
{
"id": "transfer-v4-0165",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8844190016388893,
"probabilities": [
0.8844190016388893,
0.11558099836111069
],
"target": 0,
"brier": 0.026717934364302143,
"nll": 0.12282434488491112
},
{
"id": "transfer-v4-0166",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5745761692523956,
"probabilities": [
0.5745761692523956,
0.42542383074760437
],
"target": 1,
"brier": 0.6602755485455152,
"nll": 0.8546693581620873
},
{
"id": "transfer-v4-0167",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5419460535049438,
"probabilities": [
0.5419460535049438,
0.45805394649505615
],
"target": 1,
"brier": 0.5874110498191669,
"nll": 0.7807683146971992
},
{
"id": "transfer-v4-0168",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5582027435302734,
"probabilities": [
0.44179725646972656,
0.5582027435302734
],
"target": 1,
"brier": 0.3903696316483547,
"nll": 0.5830330429327076
},
{
"id": "transfer-v4-0169",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5290116369724274,
"probabilities": [
0.5290116369724274,
0.47098836302757263
],
"target": 1,
"brier": 0.5597066241044946,
"nll": 0.7529218922187698
},
{
"id": "transfer-v4-0170",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5222960412502289,
"probabilities": [
0.5222960412502289,
0.4777039587497711
],
"target": 1,
"brier": 0.5455863094113216,
"nll": 0.7387640715161603
},
{
"id": "transfer-v4-0171",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9498938769102097,
"probabilities": [
0.9498938769102097,
0.050106123089790344
],
"target": 0,
"brier": 0.005021247142178442,
"nll": 0.05140500914298024
},
{
"id": "transfer-v4-0172",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5437692403793335,
"probabilities": [
0.4562307596206665,
0.5437692403793335
],
"target": 1,
"brier": 0.41629301204810076,
"nll": 0.6092303125995928
},
{
"id": "transfer-v4-0173",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7041691839694977,
"probabilities": [
0.7041691839694977,
0.2958308160305023
],
"target": 0,
"brier": 0.17503174342654582,
"nll": 0.35073663355738194
},
{
"id": "transfer-v4-0174",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6253270506858826,
"probabilities": [
0.37467294931411743,
0.6253270506858826
],
"target": 1,
"brier": 0.2807596378954784,
"nll": 0.46948048501213346
},
{
"id": "transfer-v4-0175",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6462122201919556,
"probabilities": [
0.6462122201919556,
0.35378777980804443
],
"target": 0,
"brier": 0.25033158628301067,
"nll": 0.43662731491948614
},
{
"id": "transfer-v4-0176",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.8458191156387329,
"probabilities": [
0.1541808843612671,
0.8458191156387329
],
"target": 0,
"brier": 1.4308199527597765,
"nll": 1.869628792066141
},
{
"id": "transfer-v4-0177",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5678901076316833,
"probabilities": [
0.43210989236831665,
0.5678901076316833
],
"target": 1,
"brier": 0.3734379181651164,
"nll": 0.565827351458631
},
{
"id": "transfer-v4-0178",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.577567845582962,
"probabilities": [
0.577567845582962,
0.42243215441703796
],
"target": 0,
"brier": 0.3568978501708404,
"nll": 0.5489293619576643
},
{
"id": "transfer-v4-0179",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8419682681560516,
"probabilities": [
0.8419682681560516,
0.15803173184394836
],
"target": 0,
"brier": 0.04994805653919521,
"nll": 0.17201295172542896
},
{
"id": "transfer-v4-0180",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9423608705401421,
"probabilities": [
0.9423608705401421,
0.05763912945985794
],
"target": 0,
"brier": 0.006644538489780527,
"nll": 0.05936698802054168
},
{
"id": "transfer-v4-0181",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5870485901832581,
"probabilities": [
0.5870485901832581,
0.41295140981674194
],
"target": 0,
"brier": 0.3410577337392695,
"nll": 0.5326476854363391
},
{
"id": "transfer-v4-0182",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6541847884654999,
"probabilities": [
0.6541847884654999,
0.3458152115345001
],
"target": 0,
"brier": 0.23917632105730213,
"nll": 0.42436541626451363
},
{
"id": "transfer-v4-0183",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5126780271530151,
"probabilities": [
0.48732197284698486,
0.5126780271530151
],
"target": 0,
"brier": 0.5256775190510155,
"nll": 0.7188302391437357
},
{
"id": "transfer-v4-0184",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5610278844833374,
"probabilities": [
0.4389721155166626,
0.5610278844833374
],
"target": 0,
"brier": 0.629504574335698,
"nll": 0.8233193861096099
},
{
"id": "transfer-v4-0185",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.6526845097541809,
"probabilities": [
0.3473154902458191,
0.6526845097541809
],
"target": 0,
"brier": 0.851994138546111,
"nll": 1.057521718309615
},
{
"id": "transfer-v4-0186",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6837470829486847,
"probabilities": [
0.6837470829486847,
0.3162529170513153
],
"target": 0,
"brier": 0.20003181508693224,
"nll": 0.38016719150925543
},
{
"id": "transfer-v4-0187",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7436029314994812,
"probabilities": [
0.7436029314994812,
0.2563970685005188
],
"target": 0,
"brier": 0.13147891347131946,
"nll": 0.29624808083562437
},
{
"id": "transfer-v4-0188",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5703235864639282,
"probabilities": [
0.4296764135360718,
0.5703235864639282
],
"target": 0,
"brier": 0.6505379865541556,
"nll": 0.8447228802451456
},
{
"id": "transfer-v4-0189",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5556381940841675,
"probabilities": [
0.4443618059158325,
0.5556381940841675
],
"target": 0,
"brier": 0.6174676054502299,
"nll": 0.8111161701940749
},
{
"id": "transfer-v4-0190",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8220205307006836,
"probabilities": [
0.1779794692993164,
0.8220205307006836
],
"target": 1,
"brier": 0.06335338298413262,
"nll": 0.19598990771635236
},
{
"id": "transfer-v4-0191",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.960529875010252,
"probabilities": [
0.960529875010252,
0.039470124989748
],
"target": 0,
"brier": 0.0031157815334126593,
"nll": 0.04027019365467989
},
{
"id": "transfer-v4-0192",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.7958254218101501,
"probabilities": [
0.7958254218101501,
0.20417457818984985
],
"target": 1,
"brier": 1.2666762039986068,
"nll": 1.5887798756645068
},
{
"id": "transfer-v4-0193",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6945277154445648,
"probabilities": [
0.6945277154445648,
0.3054722845554352
],
"target": 0,
"brier": 0.18662663326303353,
"nll": 0.3645232105363941
},
{
"id": "transfer-v4-0194",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5873855948448181,
"probabilities": [
0.4126144051551819,
0.5873855948448181
],
"target": 1,
"brier": 0.3405012946831292,
"nll": 0.5320737841056286
},
{
"id": "transfer-v4-0195",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9223754927515984,
"probabilities": [
0.9223754927515984,
0.07762450724840164
],
"target": 0,
"brier": 0.012051128251114318,
"nll": 0.08080287938328734
},
{
"id": "transfer-v4-0196",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9670990705490112,
"probabilities": [
0.9670990705490112,
0.03290092945098877
],
"target": 0,
"brier": 0.0021649423174778804,
"nll": 0.03345433732987965
},
{
"id": "transfer-v4-0197",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7410359978675842,
"probabilities": [
0.7410359978675842,
0.25896400213241577
],
"target": 0,
"brier": 0.13412470880087568,
"nll": 0.29970607474782857
},
{
"id": "transfer-v4-0198",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7426941096782684,
"probabilities": [
0.7426941096782684,
0.25730589032173157
],
"target": 0,
"brier": 0.1324126423885179,
"nll": 0.29747101529529296
},
{
"id": "transfer-v4-0199",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9379060417413712,
"probabilities": [
0.9379060417413712,
0.062093958258628845
],
"target": 0,
"brier": 0.007711319304448683,
"nll": 0.0641055037123541
},
{
"id": "transfer-v4-0200",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6874623894691467,
"probabilities": [
0.6874623894691467,
0.31253761053085327
],
"target": 0,
"brier": 0.19535951599267065,
"nll": 0.37474815716454657
},
{
"id": "transfer-v4-0201",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9082615748047829,
"probabilities": [
0.9082615748047829,
0.09173842519521713
],
"target": 0,
"brier": 0.0168318773145969,
"nll": 0.09622286388850157
},
{
"id": "transfer-v4-0202",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.938240546733141,
"probabilities": [
0.938240546733141,
0.061759453266859055
],
"target": 0,
"brier": 0.007628460135642695,
"nll": 0.06374891644207448
},
{
"id": "transfer-v4-0203",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8221616894006729,
"probabilities": [
0.8221616894006729,
0.1778383105993271
],
"target": 0,
"brier": 0.06325292943364547,
"nll": 0.1958182008354357
},
{
"id": "transfer-v4-0204",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9457333423197269,
"probabilities": [
0.9457333423197269,
0.054266657680273056
],
"target": 0,
"brier": 0.005889740271575877,
"nll": 0.05579462882027759
},
{
"id": "transfer-v4-0205",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8556381464004517,
"probabilities": [
0.14436185359954834,
0.8556381464004517
],
"target": 1,
"brier": 0.041680689549394856,
"nll": 0.15590771838198605
},
{
"id": "transfer-v4-0206",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8308289647102356,
"probabilities": [
0.8308289647102356,
0.1691710352897644
],
"target": 0,
"brier": 0.05723767836202143,
"nll": 0.18533132395016086
},
{
"id": "transfer-v4-0207",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8998828530311584,
"probabilities": [
0.8998828530311584,
0.10011714696884155
],
"target": 0,
"brier": 0.02004688623436124,
"nll": 0.10549068742851647
},
{
"id": "transfer-v4-0208",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6985904276371002,
"probabilities": [
0.6985904276371002,
0.3014095723628998
],
"target": 0,
"brier": 0.18169546062397224,
"nll": 0.3586906489118412
},
{
"id": "transfer-v4-0209",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.5840811431407928,
"probabilities": [
0.5840811431407928,
0.41591885685920715
],
"target": 0,
"brier": 0.3459769909821393,
"nll": 0.5377153620714623
},
{
"id": "transfer-v4-0210",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8891290128231049,
"probabilities": [
0.8891290128231049,
0.11087098717689514
],
"target": 0,
"brier": 0.024584751595158494,
"nll": 0.11751293271147539
},
{
"id": "transfer-v4-0211",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7850408405065536,
"probabilities": [
0.7850408405065536,
0.21495915949344635
],
"target": 0,
"brier": 0.09241488050025781,
"nll": 0.24201953643004215
},
{
"id": "transfer-v4-0212",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7116452157497406,
"probabilities": [
0.7116452157497406,
0.2883547842502594
],
"target": 0,
"brier": 0.1662969632000273,
"nll": 0.3401757842454383
},
{
"id": "transfer-v4-0213",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8715003132820129,
"probabilities": [
0.12849968671798706,
0.8715003132820129
],
"target": 1,
"brier": 0.03302433897324164,
"nll": 0.1375390545476419
},
{
"id": "transfer-v4-0214",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8732235431671143,
"probabilities": [
0.8732235431671143,
0.12677645683288574
],
"target": 0,
"brier": 0.032144540014201084,
"nll": 0.13556369272854793
},
{
"id": "transfer-v4-0215",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6545718312263489,
"probabilities": [
0.3454281687736511,
0.6545718312263489
],
"target": 1,
"brier": 0.238641239564636,
"nll": 0.4237739498813698
},
{
"id": "transfer-v4-0216",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7209542989730835,
"probabilities": [
0.7209542989730835,
0.2790457010269165
],
"target": 0,
"brier": 0.15573300652320654,
"nll": 0.32717952931906247
},
{
"id": "transfer-v4-0217",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.8323631435632706,
"probabilities": [
0.8323631435632706,
0.16763685643672943
],
"target": 1,
"brier": 1.3856568055250595,
"nll": 1.785955207969795
},
{
"id": "transfer-v4-0218",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9210368245840073,
"probabilities": [
0.9210368245840073,
0.07896317541599274
],
"target": 0,
"brier": 0.01247036614355368,
"nll": 0.08225526026445952
},
{
"id": "transfer-v4-0219",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8546906262636185,
"probabilities": [
0.8546906262636185,
0.14530937373638153
],
"target": 0,
"brier": 0.04222962819131881,
"nll": 0.15701571615283952
},
{
"id": "transfer-v4-0220",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5386393964290619,
"probabilities": [
0.5386393964290619,
0.4613606035709381
],
"target": 1,
"brier": 0.5802647987709282,
"nll": 0.7735753214329492
},
{
"id": "transfer-v4-0221",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.657749742269516,
"probabilities": [
0.657749742269516,
0.342250257730484
],
"target": 1,
"brier": 0.8652694469112294,
"nll": 1.0722130617664292
},
{
"id": "transfer-v4-0222",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5133196115493774,
"probabilities": [
0.48668038845062256,
0.5133196115493774
],
"target": 0,
"brier": 0.5269940472024075,
"nll": 0.720147657898864
},
{
"id": "transfer-v4-0223",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.6196538507938385,
"probabilities": [
0.6196538507938385,
0.3803461492061615
],
"target": 1,
"brier": 0.7679417896072653,
"nll": 0.9666735219330217
},
{
"id": "transfer-v4-0224",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8689603954553604,
"probabilities": [
0.8689603954553604,
0.1310396045446396
],
"target": 0,
"brier": 0.034342755918431056,
"nll": 0.14045772960529807
},
{
"id": "transfer-v4-0225",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6051240563392639,
"probabilities": [
0.6051240563392639,
0.3948759436607361
],
"target": 0,
"brier": 0.31185402176391364,
"nll": 0.5023217901711063
},
{
"id": "transfer-v4-0226",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.656252384185791,
"probabilities": [
0.343747615814209,
0.656252384185791
],
"target": 1,
"brier": 0.23632484675590604,
"nll": 0.42120983203788814
},
{
"id": "transfer-v4-0227",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8562991470098495,
"probabilities": [
0.8562991470098495,
0.14370085299015045
],
"target": 0,
"brier": 0.041299870300193664,
"nll": 0.15513549308519484
},
{
"id": "transfer-v4-0228",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.6920208930969238,
"probabilities": [
0.30797910690307617,
0.6920208930969238
],
"target": 0,
"brier": 0.9577858329653282,
"nll": 1.177723333039714
},
{
"id": "transfer-v4-0229",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8073985576629639,
"probabilities": [
0.8073985576629639,
0.19260144233703613
],
"target": 0,
"brier": 0.07419063118061331,
"nll": 0.213937856962014
},
{
"id": "transfer-v4-0230",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.651040256023407,
"probabilities": [
0.348959743976593,
0.651040256023407
],
"target": 1,
"brier": 0.2435458058324187,
"nll": 0.4291838014758747
},
{
"id": "transfer-v4-0231",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8151125907897949,
"probabilities": [
0.18488740921020508,
0.8151125907897949
],
"target": 1,
"brier": 0.06836670816892365,
"nll": 0.20442902707452199
},
{
"id": "transfer-v4-0232",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.9581887722015381,
"probabilities": [
0.9581887722015381,
0.041811227798461914
],
"target": 0,
"brier": 0.0034963575400297486,
"nll": 0.04271047219565321
},
{
"id": "transfer-v4-0233",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.6815144419670105,
"probabilities": [
0.6815144419670105,
0.3184855580329895
],
"target": 0,
"brier": 0.20286610135116945,
"nll": 0.38343783662913067
},
{
"id": "transfer-v4-0234",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8082143068313599,
"probabilities": [
0.8082143068313599,
0.19178569316864014
],
"target": 0,
"brier": 0.07356350420835156,
"nll": 0.21292802440169478
},
{
"id": "transfer-v4-0235",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.586908608675003,
"probabilities": [
0.586908608675003,
0.41309139132499695
],
"target": 1,
"brier": 0.6889234298736557,
"nll": 0.8840864240001475
},
{
"id": "transfer-v4-0236",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": false,
"confidence": 0.5084884762763977,
"probabilities": [
0.5084884762763977,
0.4915115237236023
],
"target": 1,
"brier": 0.5171210610117853,
"nll": 0.71026989364006
},
{
"id": "transfer-v4-0237",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7156517505645752,
"probabilities": [
0.7156517505645752,
0.2843482494354248
],
"target": 0,
"brier": 0.16170785391398113,
"nll": 0.3345616122365838
},
{
"id": "transfer-v4-0238",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.8864069879055023,
"probabilities": [
0.8864069879055023,
0.11359301209449768
],
"target": 0,
"brier": 0.025806744793401393,
"nll": 0.12057907955279323
},
{
"id": "transfer-v4-0239",
"question": "offensive",
"type": "noul",
"source": "tweet_offensive",
"error": null,
"correct": true,
"confidence": 0.7499577403068542,
"probabilities": [
0.7499577403068542,
0.25004225969314575
],
"target": 0,
"brier": 0.12504226326490908,
"nll": 0.2877384202968186
},
{
"id": "transfer-v4-0240",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.989712119102478,
"probabilities": [
0.010287880897521973,
0.989712119102478
],
"target": 1,
"brier": 0.00021168098672319502,
"nll": 0.010341166926133993
},
{
"id": "transfer-v4-0241",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9823657497763634,
"probabilities": [
0.9823657497763634,
0.017634250223636627
],
"target": 0,
"brier": 0.0006219335618996569,
"nll": 0.017791586024008058
},
{
"id": "transfer-v4-0242",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8602241277694702,
"probabilities": [
0.13977587223052979,
0.8602241277694702
],
"target": 1,
"brier": 0.039074588915610775,
"nll": 0.15056231000300058
},
{
"id": "transfer-v4-0243",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9794776663184166,
"probabilities": [
0.9794776663184166,
0.020522333681583405
],
"target": 0,
"brier": 0.0008423323594765053,
"nll": 0.02073584296171065
},
{
"id": "transfer-v4-0244",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9477681517601013,
"probabilities": [
0.05223184823989868,
0.9477681517601013
],
"target": 1,
"brier": 0.005456331941111614,
"nll": 0.05364537229207326
},
{
"id": "transfer-v4-0245",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.87665194272995,
"probabilities": [
0.12334805727005005,
0.87665194272995
],
"target": 1,
"brier": 0.030429486464591093,
"nll": 0.13164523798455632
},
{
"id": "transfer-v4-0246",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.6670540273189545,
"probabilities": [
0.6670540273189545,
0.33294597268104553
],
"target": 1,
"brier": 0.8899221507248729,
"nll": 1.0997750463657718
},
{
"id": "transfer-v4-0247",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.7525382488965988,
"probabilities": [
0.7525382488965988,
0.24746175110340118
],
"target": 0,
"brier": 0.12247463651832335,
"nll": 0.2843034545523909
},
{
"id": "transfer-v4-0248",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9945201897062361,
"probabilities": [
0.9945201897062361,
0.005479810293763876
],
"target": 0,
"brier": 6.005664171128107e-05,
"nll": 0.005494879530443382
},
{
"id": "transfer-v4-0249",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9876138595864177,
"probabilities": [
0.9876138595864177,
0.012386140413582325
],
"target": 0,
"brier": 0.00030683294868995466,
"nll": 0.012463488006486634
},
{
"id": "transfer-v4-0250",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9899978777393699,
"probabilities": [
0.9899978777393699,
0.01000212226063013
],
"target": 0,
"brier": 0.0002000848994331856,
"nll": 0.010052479553405358
},
{
"id": "transfer-v4-0251",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9109801054000854,
"probabilities": [
0.08901989459991455,
0.9109801054000854
],
"target": 1,
"brier": 0.01584908326915979,
"nll": 0.09323422016032235
},
{
"id": "transfer-v4-0252",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9342594146728516,
"probabilities": [
0.06574058532714844,
0.9342594146728516
],
"target": 1,
"brier": 0.008643649118312169,
"nll": 0.06800113341513637
},
{
"id": "transfer-v4-0253",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.729695200920105,
"probabilities": [
0.270304799079895,
0.729695200920105
],
"target": 1,
"brier": 0.14612936881124483,
"nll": 0.315128365017026
},
{
"id": "transfer-v4-0254",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9205306768417358,
"probabilities": [
0.07946932315826416,
0.9205306768417358
],
"target": 1,
"brier": 0.01263074664646524,
"nll": 0.08280495258323083
},
{
"id": "transfer-v4-0255",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9192579984664917,
"probabilities": [
0.0807420015335083,
0.9192579984664917
],
"target": 1,
"brier": 0.013038541623274114,
"nll": 0.08418845776002218
},
{
"id": "transfer-v4-0256",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.7387875318527222,
"probabilities": [
0.26121246814727783,
0.7387875318527222
],
"target": 1,
"brier": 0.13646390703118527,
"nll": 0.30274490701396417
},
{
"id": "transfer-v4-0257",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.983542799949646,
"probabilities": [
0.016457200050354004,
0.983542799949646
],
"target": 1,
"brier": 0.0005416788669947437,
"nll": 0.01659412410331411
},
{
"id": "transfer-v4-0258",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9477447308599949,
"probabilities": [
0.9477447308599949,
0.05225526914000511
],
"target": 0,
"brier": 0.005461226305788741,
"nll": 0.05367008423185733
},
{
"id": "transfer-v4-0259",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8084155321121216,
"probabilities": [
0.19158446788787842,
0.8084155321121216
],
"target": 1,
"brier": 0.07340921667176303,
"nll": 0.21267908023778842
},
{
"id": "transfer-v4-0260",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.995261924341321,
"probabilities": [
0.995261924341321,
0.0047380756586790085
],
"target": 0,
"brier": 4.489872189473304e-05,
"nll": 0.004749335921215829
},
{
"id": "transfer-v4-0261",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.857149749994278,
"probabilities": [
0.857149749994278,
0.14285025000572205
],
"target": 0,
"brier": 0.04081238785339458,
"nll": 0.15414263819960133
},
{
"id": "transfer-v4-0262",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9038894772529602,
"probabilities": [
0.0961105227470398,
0.9038894772529602
],
"target": 1,
"brier": 0.018474465165418508,
"nll": 0.10104818574021292
},
{
"id": "transfer-v4-0263",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9392521977424622,
"probabilities": [
0.06074780225753784,
0.9392521977424622
],
"target": 1,
"brier": 0.007380590958241839,
"nll": 0.06267125463996623
},
{
"id": "transfer-v4-0264",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9881893396377563,
"probabilities": [
0.011810660362243652,
0.9881893396377563
],
"target": 1,
"brier": 0.0002789833963845467,
"nll": 0.011880960285266029
},
{
"id": "transfer-v4-0265",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9901415510103106,
"probabilities": [
0.9901415510103106,
0.00985844898968935
],
"target": 0,
"brier": 0.00019437803296461394,
"nll": 0.009907365255788825
},
{
"id": "transfer-v4-0266",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.7788053601980209,
"probabilities": [
0.7788053601980209,
0.22119463980197906
],
"target": 1,
"brier": 1.2130755781463383,
"nll": 1.5087122419875156
},
{
"id": "transfer-v4-0267",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9867266369983554,
"probabilities": [
0.9867266369983554,
0.013273363001644611
],
"target": 0,
"brier": 0.0003523643307468561,
"nll": 0.013362241437638709
},
{
"id": "transfer-v4-0268",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.5668693482875824,
"probabilities": [
0.5668693482875824,
0.4331306517124176
],
"target": 0,
"brier": 0.3752043229056472,
"nll": 0.5676264281071641
},
{
"id": "transfer-v4-0269",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9836392663419247,
"probabilities": [
0.9836392663419247,
0.016360733658075333
],
"target": 0,
"brier": 0.0005353472116609581,
"nll": 0.016496048389826285
},
{
"id": "transfer-v4-0270",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8878868967294693,
"probabilities": [
0.8878868967294693,
0.1121131032705307
],
"target": 0,
"brier": 0.025138695849897363,
"nll": 0.11891091264992423
},
{
"id": "transfer-v4-0271",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8164281845092773,
"probabilities": [
0.18357181549072266,
0.8164281845092773
],
"target": 1,
"brier": 0.06739722288511985,
"nll": 0.20281632572554728
},
{
"id": "transfer-v4-0272",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.6834141612052917,
"probabilities": [
0.31658583879470825,
0.6834141612052917
],
"target": 1,
"brier": 0.200453186650698,
"nll": 0.38065421782220443
},
{
"id": "transfer-v4-0273",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.6639599204063416,
"probabilities": [
0.33604007959365845,
0.6639599204063416
],
"target": 1,
"brier": 0.2258458701866246,
"nll": 0.4095334921613146
},
{
"id": "transfer-v4-0274",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.7285807728767395,
"probabilities": [
0.2714192271232605,
0.7285807728767395
],
"target": 1,
"brier": 0.14733679370437613,
"nll": 0.31665678389018603
},
{
"id": "transfer-v4-0275",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9748811721801758,
"probabilities": [
0.02511882781982422,
0.9748811721801758
],
"target": 1,
"brier": 0.0012619110220839502,
"nll": 0.025439690098612213
},
{
"id": "transfer-v4-0276",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.9486086219549179,
"probabilities": [
0.9486086219549179,
0.05139137804508209
],
"target": 1,
"brier": 1.7997166352944167,
"nll": 2.968284862904911
},
{
"id": "transfer-v4-0277",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9817332029342651,
"probabilities": [
0.018266797065734863,
0.9817332029342651
],
"target": 1,
"brier": 0.0006673517500814796,
"nll": 0.01843569498103828
},
{
"id": "transfer-v4-0278",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9884591670706868,
"probabilities": [
0.9884591670706868,
0.011540832929313183
],
"target": 0,
"brier": 0.000266381649404639,
"nll": 0.011607945195642627
},
{
"id": "transfer-v4-0279",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.5970833003520966,
"probabilities": [
0.5970833003520966,
0.40291669964790344
],
"target": 0,
"brier": 0.32468373371031767,
"nll": 0.515698643745109
},
{
"id": "transfer-v4-0280",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9847991988062859,
"probabilities": [
0.9847991988062859,
0.015200801193714142
],
"target": 0,
"brier": 0.00046212871386164256,
"nll": 0.015317517672047696
},
{
"id": "transfer-v4-0281",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9853517636656761,
"probabilities": [
0.9853517636656761,
0.014648236334323883
],
"target": 0,
"brier": 0.0004291416554124128,
"nll": 0.014756581089618848
},
{
"id": "transfer-v4-0282",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9985299279214814,
"probabilities": [
0.9985299279214814,
0.0014700720785185695
],
"target": 0,
"brier": 4.322223832079814e-06,
"nll": 0.0014711536946423276
},
{
"id": "transfer-v4-0283",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8268019556999207,
"probabilities": [
0.17319804430007935,
0.8268019556999207
],
"target": 1,
"brier": 0.059995125098744495,
"nll": 0.19019008579280194
},
{
"id": "transfer-v4-0284",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9927478386089206,
"probabilities": [
0.9927478386089206,
0.007252161391079426
],
"target": 0,
"brier": 0.00010518768968452614,
"nll": 0.0072785861487488016
},
{
"id": "transfer-v4-0285",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9905183101072907,
"probabilities": [
0.9905183101072907,
0.009481689892709255
],
"target": 0,
"brier": 0.0001798048864430097,
"nll": 0.009526927292743893
},
{
"id": "transfer-v4-0286",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.983363151550293,
"probabilities": [
0.01663684844970703,
0.983363151550293
],
"target": 1,
"brier": 0.0005535694526770385,
"nll": 0.01677679516566519
},
{
"id": "transfer-v4-0287",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.6748564839363098,
"probabilities": [
0.3251435160636902,
0.6748564839363098
],
"target": 1,
"brier": 0.21143661207651832,
"nll": 0.3932552271063285
},
{
"id": "transfer-v4-0288",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9908135570585728,
"probabilities": [
0.9908135570585728,
0.00918644294142723
],
"target": 0,
"brier": 0.00016878146783219639,
"nll": 0.009228898518907333
},
{
"id": "transfer-v4-0289",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.6419466733932495,
"probabilities": [
0.6419466733932495,
0.3580533266067505
],
"target": 0,
"brier": 0.2564043693883207,
"nll": 0.4432500419925089
},
{
"id": "transfer-v4-0290",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9841901417821646,
"probabilities": [
0.9841901417821646,
0.015809858217835426
],
"target": 0,
"brier": 0.0004999032337361167,
"nll": 0.01593616707861531
},
{
"id": "transfer-v4-0291",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8664593249559402,
"probabilities": [
0.8664593249559402,
0.13354067504405975
],
"target": 0,
"brier": 0.03566622378244633,
"nll": 0.14334011269868507
},
{
"id": "transfer-v4-0292",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9599699378013611,
"probabilities": [
0.040030062198638916,
0.9599699378013611
],
"target": 1,
"brier": 0.0032048117592538006,
"nll": 0.04085330980082228
},
{
"id": "transfer-v4-0293",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9772359728813171,
"probabilities": [
0.02276402711868286,
0.9772359728813171
],
"target": 1,
"brier": 0.0010364018613202575,
"nll": 0.023027128076639095
},
{
"id": "transfer-v4-0294",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9735625386238098,
"probabilities": [
0.026437461376190186,
0.9735625386238098
],
"target": 1,
"brier": 0.0013978787280350957,
"nll": 0.026793215222657568
},
{
"id": "transfer-v4-0295",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.6279574632644653,
"probabilities": [
0.6279574632644653,
0.37204253673553467
],
"target": 1,
"brier": 0.7886611513390847,
"nll": 0.988747085182738
},
{
"id": "transfer-v4-0296",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9937617271207273,
"probabilities": [
0.9937617271207273,
0.006238272879272699
],
"target": 0,
"brier": 7.783209703253859e-05,
"nll": 0.006257812207021615
},
{
"id": "transfer-v4-0297",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9692113287746906,
"probabilities": [
0.9692113287746906,
0.030788671225309372
],
"target": 0,
"brier": 0.0018958845516403866,
"nll": 0.03127260131867547
},
{
"id": "transfer-v4-0298",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9720472097396851,
"probabilities": [
0.02795279026031494,
0.9720472097396851
],
"target": 1,
"brier": 0.0015627169666743157,
"nll": 0.02835090601013322
},
{
"id": "transfer-v4-0299",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9705584049224854,
"probabilities": [
0.02944159507751465,
0.9705584049224854
],
"target": 1,
"brier": 0.0017336150414166696,
"nll": 0.029883697944277934
},
{
"id": "transfer-v4-0300",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.8713530898094177,
"probabilities": [
0.8713530898094177,
0.12864691019058228
],
"target": 1,
"brier": 1.5185124142408384,
"nll": 2.0506837577166657
},
{
"id": "transfer-v4-0301",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9861700078472495,
"probabilities": [
0.9861700078472495,
0.013829992152750492
],
"target": 0,
"brier": 0.0003825373658902804,
"nll": 0.013926517490649092
},
{
"id": "transfer-v4-0302",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9775911625474691,
"probabilities": [
0.9775911625474691,
0.02240883745253086
],
"target": 0,
"brier": 0.0010043119919478996,
"nll": 0.02266373055301828
},
{
"id": "transfer-v4-0303",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9279511570930481,
"probabilities": [
0.0720488429069519,
0.9279511570930481
],
"target": 1,
"brier": 0.010382071528461267,
"nll": 0.0747761800239082
},
{
"id": "transfer-v4-0304",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.7334155440330505,
"probabilities": [
0.7334155440330505,
0.26658445596694946
],
"target": 1,
"brier": 1.075796720458591,
"nll": 1.3220641776374285
},
{
"id": "transfer-v4-0305",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9593847393989563,
"probabilities": [
0.0406152606010437,
0.9593847393989563
],
"target": 1,
"brier": 0.0032991987873813855,
"nll": 0.04146309644160274
},
{
"id": "transfer-v4-0306",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8454969525337219,
"probabilities": [
0.8454969525337219,
0.15450304746627808
],
"target": 0,
"brier": 0.04774238335273395,
"nll": 0.1678307149862225
},
{
"id": "transfer-v4-0307",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9729808568954468,
"probabilities": [
0.027019143104553223,
0.9729808568954468
],
"target": 1,
"brier": 0.001460068188208652,
"nll": 0.027390871300622625
},
{
"id": "transfer-v4-0308",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9747419413179159,
"probabilities": [
0.9747419413179159,
0.025258058682084084
],
"target": 0,
"brier": 0.0012759390567752063,
"nll": 0.025582518588418885
},
{
"id": "transfer-v4-0309",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9488758146762848,
"probabilities": [
0.9488758146762848,
0.05112418532371521
],
"target": 0,
"brier": 0.005227364650027155,
"nll": 0.05247734807486088
},
{
"id": "transfer-v4-0310",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.7273017168045044,
"probabilities": [
0.7273017168045044,
0.2726982831954956
],
"target": 0,
"brier": 0.14872870731554144,
"nll": 0.3184138713067539
},
{
"id": "transfer-v4-0311",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8008711338043213,
"probabilities": [
0.1991288661956787,
0.8008711338043213
],
"target": 1,
"brier": 0.07930461070475303,
"nll": 0.22205522649916268
},
{
"id": "transfer-v4-0312",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9908906817436218,
"probabilities": [
0.009109318256378174,
0.9908906817436218
],
"target": 1,
"brier": 0.00016595935819196939,
"nll": 0.009151061792742169
},
{
"id": "transfer-v4-0313",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.6650013029575348,
"probabilities": [
0.6650013029575348,
0.3349986970424652
],
"target": 0,
"brier": 0.22444825404029878,
"nll": 0.40796627899356364
},
{
"id": "transfer-v4-0314",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9585229754447937,
"probabilities": [
0.0414770245552063,
0.9585229754447937
],
"target": 1,
"brier": 0.0034406871319063725,
"nll": 0.04236174657527459
},
{
"id": "transfer-v4-0315",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8777196407318115,
"probabilities": [
0.12228035926818848,
0.8777196407318115
],
"target": 1,
"brier": 0.029904972525514495,
"nll": 0.13042805213436756
},
{
"id": "transfer-v4-0316",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": false,
"confidence": 0.5864621996879578,
"probabilities": [
0.5864621996879578,
0.41353780031204224
],
"target": 1,
"brier": 0.6878758233256761,
"nll": 0.8830063531897812
},
{
"id": "transfer-v4-0317",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9912212891504169,
"probabilities": [
0.9912212891504169,
0.008778710849583149
],
"target": 0,
"brier": 0.00015413152836117779,
"nll": 0.008817470739647606
},
{
"id": "transfer-v4-0318",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.9244954288005829,
"probabilities": [
0.9244954288005829,
0.07550457119941711
],
"target": 0,
"brier": 0.011401880544015697,
"nll": 0.07850717267709739
},
{
"id": "transfer-v4-0319",
"question": "answers",
"type": "noul",
"source": "qnli",
"error": null,
"correct": true,
"confidence": 0.8466399908065796,
"probabilities": [
0.8466399908065796,
0.1533600091934204
],
"target": 0,
"brier": 0.047038584839611985,
"nll": 0.16647971505538064
},
{
"id": "transfer-v4-0320",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.6184796690940857,
"probabilities": [
0.3815203309059143,
0.6184796690940857
],
"target": 0,
"brier": 0.7650342021654595,
"nll": 0.9635911376568495
},
{
"id": "transfer-v4-0321",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5048254728317261,
"probabilities": [
0.5048254728317261,
0.4951745271682739
],
"target": 0,
"brier": 0.4903956247126473,
"nll": 0.6835425077926685
},
{
"id": "transfer-v4-0322",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9746898710727692,
"probabilities": [
0.9746898710727692,
0.025310128927230835
],
"target": 0,
"brier": 0.0012812052526260942,
"nll": 0.025635939533771447
},
{
"id": "transfer-v4-0323",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9744201898574829,
"probabilities": [
0.02557981014251709,
0.9744201898574829
],
"target": 1,
"brier": 0.0013086533738544404,
"nll": 0.025912661944078492
},
{
"id": "transfer-v4-0324",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9353477954864502,
"probabilities": [
0.0646522045135498,
0.9353477954864502
],
"target": 1,
"brier": 0.00835981509692374,
"nll": 0.06683684507624653
},
{
"id": "transfer-v4-0325",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.808667004108429,
"probabilities": [
0.19133299589157104,
0.808667004108429
],
"target": 0,
"brier": 1.3078846470674037,
"nll": 1.6537399349651394
},
{
"id": "transfer-v4-0326",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.7353103160858154,
"probabilities": [
0.26468968391418457,
0.7353103160858154
],
"target": 0,
"brier": 1.0813625218844436,
"nll": 1.3291971432543468
},
{
"id": "transfer-v4-0327",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9631268978118896,
"probabilities": [
0.03687310218811035,
0.9631268978118896
],
"target": 1,
"brier": 0.002719251329949657,
"nll": 0.03757010243661359
},
{
"id": "transfer-v4-0328",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9534240365028381,
"probabilities": [
0.046575963497161865,
0.9534240365028381
],
"target": 1,
"brier": 0.004338640751377909,
"nll": 0.04769552517737897
},
{
"id": "transfer-v4-0329",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8356757760047913,
"probabilities": [
0.16432422399520874,
0.8356757760047913
],
"target": 1,
"brier": 0.05400490118325507,
"nll": 0.1795145688675306
},
{
"id": "transfer-v4-0330",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8647709041833878,
"probabilities": [
0.8647709041833878,
0.13522909581661224
],
"target": 0,
"brier": 0.03657381671075699,
"nll": 0.14529065778442948
},
{
"id": "transfer-v4-0331",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9467350840568542,
"probabilities": [
0.05326491594314575,
0.9467350840568542
],
"target": 1,
"brier": 0.005674302540860765,
"nll": 0.054735967215439094
},
{
"id": "transfer-v4-0332",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.7618682980537415,
"probabilities": [
0.23813170194625854,
0.7618682980537415
],
"target": 1,
"brier": 0.11341341494364343,
"nll": 0.2719815754333752
},
{
"id": "transfer-v4-0333",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9043905735015869,
"probabilities": [
0.09560942649841309,
0.9043905735015869
],
"target": 1,
"brier": 0.01828232487071091,
"nll": 0.10049396156321756
},
{
"id": "transfer-v4-0334",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.6111325621604919,
"probabilities": [
0.38886743783950806,
0.6111325621604919
],
"target": 1,
"brier": 0.3024357684237273,
"nll": 0.49244138399667636
},
{
"id": "transfer-v4-0335",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8314434885978699,
"probabilities": [
0.16855651140213013,
0.8314434885978699
],
"target": 1,
"brier": 0.05682259507211285,
"nll": 0.18459194586035738
},
{
"id": "transfer-v4-0336",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.7090436816215515,
"probabilities": [
0.2909563183784485,
0.7090436816215515
],
"target": 1,
"brier": 0.16931115840868216,
"nll": 0.3438381441622939
},
{
"id": "transfer-v4-0337",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9045786261558533,
"probabilities": [
0.09542137384414673,
0.9045786261558533
],
"target": 1,
"brier": 0.01821047717260882,
"nll": 0.10028605016817624
},
{
"id": "transfer-v4-0338",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.990590495057404,
"probabilities": [
0.990590495057404,
0.009409504942595959
],
"target": 0,
"brier": 0.00017707756652947555,
"nll": 0.009454054010916002
},
{
"id": "transfer-v4-0339",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9087133407592773,
"probabilities": [
0.09128665924072266,
0.9087133407592773
],
"target": 1,
"brier": 0.01666650831066363,
"nll": 0.09572559124050398
},
{
"id": "transfer-v4-0340",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.7741125822067261,
"probabilities": [
0.22588741779327393,
0.7741125822067261
],
"target": 1,
"brier": 0.10205025103462617,
"nll": 0.25603796092251996
},
{
"id": "transfer-v4-0341",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8100929260253906,
"probabilities": [
0.18990707397460938,
0.8100929260253906
],
"target": 1,
"brier": 0.07212939349119551,
"nll": 0.21060631440775213
},
{
"id": "transfer-v4-0342",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.7980794906616211,
"probabilities": [
0.2019205093383789,
0.7980794906616211
],
"target": 1,
"brier": 0.08154378418294073,
"nll": 0.2255470741353886
},
{
"id": "transfer-v4-0343",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9680332355201244,
"probabilities": [
0.9680332355201244,
0.031966764479875565
],
"target": 0,
"brier": 0.002043748062623668,
"nll": 0.03248885807996112
},
{
"id": "transfer-v4-0344",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.6367948651313782,
"probabilities": [
0.3632051348686218,
0.6367948651313782
],
"target": 1,
"brier": 0.26383593998986754,
"nll": 0.45130770803444586
},
{
"id": "transfer-v4-0345",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9556587338447571,
"probabilities": [
0.04434126615524292,
0.9556587338447571
],
"target": 1,
"brier": 0.0039322957685001825,
"nll": 0.04535440262648722
},
{
"id": "transfer-v4-0346",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9728737361729145,
"probabilities": [
0.9728737361729145,
0.027126263827085495
],
"target": 0,
"brier": 0.001471668378433294,
"nll": 0.02750097276763057
},
{
"id": "transfer-v4-0347",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8764610439538956,
"probabilities": [
0.8764610439538956,
0.12353895604610443
],
"target": 0,
"brier": 0.030523747321922645,
"nll": 0.13186302061266864
},
{
"id": "transfer-v4-0348",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9046791195869446,
"probabilities": [
0.09532088041305542,
0.9046791195869446
],
"target": 1,
"brier": 0.018172140485440025,
"nll": 0.10017496214721172
},
{
"id": "transfer-v4-0349",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9215094372630119,
"probabilities": [
0.9215094372630119,
0.07849056273698807
],
"target": 0,
"brier": 0.01232153687753812,
"nll": 0.08174226072772535
},
{
"id": "transfer-v4-0350",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9167297184467316,
"probabilities": [
0.9167297184467316,
0.08327028155326843
],
"target": 0,
"brier": 0.013867879579921194,
"nll": 0.08694259559505332
},
{
"id": "transfer-v4-0351",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.6254012584686279,
"probabilities": [
0.37459874153137207,
0.6254012584686279
],
"target": 0,
"brier": 0.7822534681882871,
"nll": 0.9818998484775997
},
{
"id": "transfer-v4-0352",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8144934177398682,
"probabilities": [
0.18550658226013184,
0.8144934177398682
],
"target": 1,
"brier": 0.06882538412367012,
"nll": 0.20518893232337518
},
{
"id": "transfer-v4-0353",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.6562073826789856,
"probabilities": [
0.3437926173210144,
0.6562073826789856
],
"target": 1,
"brier": 0.2363867274488669,
"nll": 0.4212784078646818
},
{
"id": "transfer-v4-0354",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5648004412651062,
"probabilities": [
0.4351995587348938,
0.5648004412651062
],
"target": 1,
"brier": 0.37879731184609255,
"nll": 0.5712828115266638
},
{
"id": "transfer-v4-0355",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.6261847019195557,
"probabilities": [
0.37381529808044434,
0.6261847019195557
],
"target": 0,
"brier": 0.7842145618361656,
"nll": 0.9839934589542287
},
{
"id": "transfer-v4-0356",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9871032228693366,
"probabilities": [
0.9871032228693366,
0.012896777130663395
],
"target": 0,
"brier": 0.0003326537207160047,
"nll": 0.012980662575947178
},
{
"id": "transfer-v4-0357",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9213652610778809,
"probabilities": [
0.07863473892211914,
0.9213652610778809
],
"target": 1,
"brier": 0.012366844330699678,
"nll": 0.08189872951592352
},
{
"id": "transfer-v4-0358",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9091010093688965,
"probabilities": [
0.09089899063110352,
0.9091010093688965
],
"target": 1,
"brier": 0.01652525299550689,
"nll": 0.09529906956025772
},
{
"id": "transfer-v4-0359",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9217769503593445,
"probabilities": [
0.07822304964065552,
0.9217769503593445
],
"target": 1,
"brier": 0.012237690990168915,
"nll": 0.08145200404270121
},
{
"id": "transfer-v4-0360",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.7595505714416504,
"probabilities": [
0.2404494285583496,
0.7595505714416504
],
"target": 0,
"brier": 1.1538341411546753,
"nll": 1.4252454878121332
},
{
"id": "transfer-v4-0361",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.7371609807014465,
"probabilities": [
0.26283901929855347,
0.7371609807014465
],
"target": 1,
"brier": 0.13816870013165072,
"nll": 0.30494898364118556
},
{
"id": "transfer-v4-0362",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.7929844260215759,
"probabilities": [
0.20701557397842407,
0.7929844260215759
],
"target": 0,
"brier": 1.2576485998255365,
"nll": 1.5749612519361555
},
{
"id": "transfer-v4-0363",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.844094455242157,
"probabilities": [
0.15590554475784302,
0.844094455242157
],
"target": 1,
"brier": 0.048613077772479585,
"nll": 0.16949087685403652
},
{
"id": "transfer-v4-0364",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9647847451269627,
"probabilities": [
0.9647847451269627,
0.03521525487303734
],
"target": 0,
"brier": 0.00248022835154596,
"nll": 0.0358502645697875
},
{
"id": "transfer-v4-0365",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9167624935507774,
"probabilities": [
0.9167624935507774,
0.08323750644922256
],
"target": 0,
"brier": 0.013856964959768736,
"nll": 0.08690684403435958
},
{
"id": "transfer-v4-0366",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9722596313804388,
"probabilities": [
0.9722596313804388,
0.027740368619561195
],
"target": 0,
"brier": 0.001539056102298271,
"nll": 0.028132399715646756
},
{
"id": "transfer-v4-0367",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8713620901107788,
"probabilities": [
0.1286379098892212,
0.8713620901107788
],
"target": 1,
"brier": 0.03309542372133478,
"nll": 0.1376976708230918
},
{
"id": "transfer-v4-0368",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.827747255563736,
"probabilities": [
0.827747255563736,
0.17225274443626404
],
"target": 0,
"brier": 0.05934201593164978,
"nll": 0.18904741809789669
},
{
"id": "transfer-v4-0369",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.6498607695102692,
"probabilities": [
0.6498607695102692,
0.35013923048973083
],
"target": 0,
"brier": 0.2451949614558817,
"nll": 0.4309971397901442
},
{
"id": "transfer-v4-0370",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9762519970536232,
"probabilities": [
0.9762519970536232,
0.0237480029463768
],
"target": 0,
"brier": 0.0011279352878822424,
"nll": 0.024034532192819483
},
{
"id": "transfer-v4-0371",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.5763038396835327,
"probabilities": [
0.4236961603164673,
0.5763038396835327
],
"target": 0,
"brier": 0.664252231267966,
"nll": 0.8587386836600577
},
{
"id": "transfer-v4-0372",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9694753922522068,
"probabilities": [
0.9694753922522068,
0.030524607747793198
],
"target": 0,
"brier": 0.001863503356313273,
"nll": 0.0310001865171656
},
{
"id": "transfer-v4-0373",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.9812983367592096,
"probabilities": [
0.9812983367592096,
0.018701663240790367
],
"target": 1,
"brier": 1.9258928514527824,
"nll": 3.9791428157190483
},
{
"id": "transfer-v4-0374",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.894832968711853,
"probabilities": [
0.10516703128814697,
0.894832968711853
],
"target": 0,
"brier": 1.6014520837873363,
"nll": 2.2522054185927676
},
{
"id": "transfer-v4-0375",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9820812959223986,
"probabilities": [
0.9820812959223986,
0.017918704077601433
],
"target": 0,
"brier": 0.0006421599116413004,
"nll": 0.018081187982559914
},
{
"id": "transfer-v4-0376",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5621512234210968,
"probabilities": [
0.5621512234210968,
0.4378487765789032
],
"target": 0,
"brier": 0.3834231023032846,
"nll": 0.5759843844637401
},
{
"id": "transfer-v4-0377",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9912121156230569,
"probabilities": [
0.9912121156230569,
0.008787884376943111
],
"target": 0,
"brier": 0.00015445382364504164,
"nll": 0.008826725554803506
},
{
"id": "transfer-v4-0378",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.8995331525802612,
"probabilities": [
0.10046684741973877,
0.8995331525802612
],
"target": 0,
"brier": 1.618319785181967,
"nll": 2.2979274823247113
},
{
"id": "transfer-v4-0379",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9797699544578791,
"probabilities": [
0.9797699544578791,
0.020230045542120934
],
"target": 0,
"brier": 0.0008185094852725741,
"nll": 0.020437475222450586
},
{
"id": "transfer-v4-0380",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5145702958106995,
"probabilities": [
0.5145702958106995,
0.48542970418930054
],
"target": 0,
"brier": 0.47128399541862365,
"nll": 0.6644231036712968
},
{
"id": "transfer-v4-0381",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.5862615704536438,
"probabilities": [
0.4137384295463562,
0.5862615704536438
],
"target": 0,
"brier": 0.6874052579815455,
"nll": 0.8825213175245316
},
{
"id": "transfer-v4-0382",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.88202965259552,
"probabilities": [
0.11797034740447998,
0.88202965259552
],
"target": 0,
"brier": 1.5559526161155475,
"nll": 2.137321979278268
},
{
"id": "transfer-v4-0383",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9144811630249023,
"probabilities": [
0.08551883697509766,
0.9144811630249023
],
"target": 1,
"brier": 0.01462694295514666,
"nll": 0.08939840947719085
},
{
"id": "transfer-v4-0384",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9536455869674683,
"probabilities": [
0.04635441303253174,
0.9536455869674683
],
"target": 1,
"brier": 0.0042974632151810965,
"nll": 0.04746317868839901
},
{
"id": "transfer-v4-0385",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.960571501404047,
"probabilities": [
0.960571501404047,
0.03942849859595299
],
"target": 0,
"brier": 0.0031092130030621334,
"nll": 0.040226857686768376
},
{
"id": "transfer-v4-0386",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.8801729679107666,
"probabilities": [
0.1198270320892334,
0.8801729679107666
],
"target": 0,
"brier": 1.5494089068816947,
"nll": 2.1217059752717002
},
{
"id": "transfer-v4-0387",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.98795095551759,
"probabilities": [
0.98795095551759,
0.012049044482409954
],
"target": 0,
"brier": 0.0002903589458781875,
"nll": 0.012122222630765516
},
{
"id": "transfer-v4-0388",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8157898783683777,
"probabilities": [
0.18421012163162231,
0.8157898783683777
],
"target": 1,
"brier": 0.06786673782307417,
"nll": 0.2035984591768996
},
{
"id": "transfer-v4-0389",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8502814173698425,
"probabilities": [
0.14971858263015747,
0.8502814173698425
],
"target": 1,
"brier": 0.04483130796956658,
"nll": 0.16218790503378047
},
{
"id": "transfer-v4-0390",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9855957869440317,
"probabilities": [
0.9855957869440317,
0.014404213055968285
],
"target": 0,
"brier": 0.0004149627075234544,
"nll": 0.014508960822375325
},
{
"id": "transfer-v4-0391",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.6375292539596558,
"probabilities": [
0.6375292539596558,
0.36247074604034424
],
"target": 0,
"brier": 0.26277008347008746,
"nll": 0.4501551144382379
},
{
"id": "transfer-v4-0392",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.9509166479110718,
"probabilities": [
0.04908335208892822,
0.9509166479110718
],
"target": 0,
"brier": 1.8084849425488585,
"nll": 3.0142353630012404
},
{
"id": "transfer-v4-0393",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.8400011360645294,
"probabilities": [
0.8400011360645294,
0.15999886393547058
],
"target": 0,
"brier": 0.05119927292128246,
"nll": 0.1743520346879192
},
{
"id": "transfer-v4-0394",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.859830915927887,
"probabilities": [
0.859830915927887,
0.14016908407211304
],
"target": 0,
"brier": 0.039294744259230185,
"nll": 0.15101951845092065
},
{
"id": "transfer-v4-0395",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.5634728074073792,
"probabilities": [
0.5634728074073792,
0.43652719259262085
],
"target": 0,
"brier": 0.3811119797455902,
"nll": 0.5736362032640682
},
{
"id": "transfer-v4-0396",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": false,
"confidence": 0.7741358131170273,
"probabilities": [
0.7741358131170273,
0.22586418688297272
],
"target": 1,
"brier": 1.198572514300722,
"nll": 1.4878214033441617
},
{
"id": "transfer-v4-0397",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9769919421523809,
"probabilities": [
0.9769919421523809,
0.023008057847619057
],
"target": 0,
"brier": 0.0010587414518387697,
"nll": 0.02327687451442898
},
{
"id": "transfer-v4-0398",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.7990437000989914,
"probabilities": [
0.7990437000989914,
0.2009562999010086
],
"target": 0,
"brier": 0.08076686893980822,
"nll": 0.2243396412208943
},
{
"id": "transfer-v4-0399",
"question": "paraphrase",
"type": "noul",
"source": "paws",
"error": null,
"correct": true,
"confidence": 0.9209640026092529,
"probabilities": [
0.07903599739074707,
0.9209640026092529
],
"target": 1,
"brier": 0.012493377767100355,
"nll": 0.08233432860549088
},
{
"id": "transfer-v4-0400",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9855674675041792,
"probabilities": [
0.0014505475078105264,
0.9855674675041792,
0.008854454535811589,
0.00412753045219864
],
"target": 1,
"brier": 0.00030583995507591936,
"nll": 0.014537694555911123
},
{
"id": "transfer-v4-0401",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7833765078364952,
"probabilities": [
0.08174639743356091,
0.07219910360717723,
0.06267799112276673,
0.7833765078364952
],
"target": 3,
"brier": 0.06274945198334328,
"nll": 0.24414184564387925
},
{
"id": "transfer-v4-0402",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9921071703703471,
"probabilities": [
0.9921071703703471,
0.003952485816123434,
0.0013677512659097666,
0.0025725925476196257
],
"target": 0,
"brier": 8.640787963084908e-05,
"nll": 0.007924142885059176
},
{
"id": "transfer-v4-0403",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9699022454904943,
"probabilities": [
0.0017907659640042455,
0.003415994700852022,
0.02489099384464937,
0.9699022454904943
],
"target": 3,
"brier": 0.0015403122636229282,
"nll": 0.03055999040798798
},
{
"id": "transfer-v4-0404",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8304950788266743,
"probabilities": [
0.004064866436293033,
0.8304950788266743,
0.15712549158198508,
0.00831456315504767
],
"target": 1,
"brier": 0.05350599350646001,
"nll": 0.1857332755012211
},
{
"id": "transfer-v4-0405",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9639441388918909,
"probabilities": [
0.9639441388918909,
0.014388388980903456,
0.008093754775996794,
0.013573717351208846
],
"target": 0,
"brier": 0.0017568055268175175,
"nll": 0.03672193325817779
},
{
"id": "transfer-v4-0406",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.987878555697235,
"probabilities": [
0.0014657430224854855,
0.987878555697235,
0.00564103837387754,
0.005014662906401894
],
"target": 1,
"brier": 0.00020604597259340007,
"nll": 0.012195508124252144
},
{
"id": "transfer-v4-0407",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9896873908942863,
"probabilities": [
0.0009431039289557332,
0.9896873908942863,
0.0025975099036043003,
0.0067719952731537265
],
"target": 1,
"brier": 0.0001598463292670006,
"nll": 0.010366152491774654
},
{
"id": "transfer-v4-0408",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9353662321185329,
"probabilities": [
0.9353662321185329,
0.039165928517406405,
0.009876031325052324,
0.015591808039008382
],
"target": 0,
"brier": 0.006052134379844662,
"nll": 0.06681713427939441
},
{
"id": "transfer-v4-0409",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9861214871765287,
"probabilities": [
0.0036591138185364407,
0.005589931337045637,
0.004629467667889172,
0.9861214871765287
],
"target": 3,
"brier": 0.00025868153536917767,
"nll": 0.01397571982291389
},
{
"id": "transfer-v4-0410",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9765027489196034,
"probabilities": [
0.01786415042839199,
0.005266244376396582,
0.0003668562756080555,
0.9765027489196034
],
"target": 3,
"brier": 0.0008991165922222975,
"nll": 0.02377771359552711
},
{
"id": "transfer-v4-0411",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9845804860948448,
"probabilities": [
0.010230340363695958,
0.004225625780510914,
0.9845804860948448,
0.0009635477609483102
],
"target": 2,
"brier": 0.00036120561055288735,
"nll": 0.015539630974035146
},
{
"id": "transfer-v4-0412",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.953325729132784,
"probabilities": [
0.0018872355194321157,
0.006919728451870295,
0.953325729132784,
0.037867306895913624
],
"target": 2,
"brier": 0.0036638647922889837,
"nll": 0.04779864030230303
},
{
"id": "transfer-v4-0413",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9765417512172905,
"probabilities": [
0.9765417512172905,
0.009509145220216349,
0.006667913359892188,
0.0072811902026009455
],
"target": 0,
"brier": 0.000738190078112137,
"nll": 0.023737773596526058
},
{
"id": "transfer-v4-0414",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.99498580832224,
"probabilities": [
0.003227345145576586,
0.0011484068696730508,
0.0006384396625102953,
0.99498580832224
],
"target": 3,
"brier": 3.728431841097252e-05,
"nll": 0.005026804917985309
},
{
"id": "transfer-v4-0415",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9781309539937094,
"probabilities": [
0.0013928949997756887,
0.9781309539937094,
0.012760493977239114,
0.0077156570292758
],
"target": 1,
"brier": 0.0007025568996422229,
"nll": 0.022111718122027384
},
{
"id": "transfer-v4-0416",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.6511333257321272,
"probabilities": [
0.24619603409004784,
0.02808612257554138,
0.07458451760228356,
0.6511333257321272
],
"target": 3,
"brier": 0.18867212416368773,
"nll": 0.42904085631067906
},
{
"id": "transfer-v4-0417",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9764625684739574,
"probabilities": [
0.9764625684739574,
0.009536785322269415,
0.007361793616907877,
0.006638852586865306
],
"target": 0,
"brier": 0.0007432313260542709,
"nll": 0.02381886173604331
},
{
"id": "transfer-v4-0418",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.978014469602152,
"probabilities": [
0.978014469602152,
0.010971616027397857,
0.004271247426174231,
0.006742666944275921
],
"target": 0,
"brier": 0.0006674470172243835,
"nll": 0.022230813962541104
},
{
"id": "transfer-v4-0419",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9920482987861392,
"probabilities": [
0.9920482987861392,
0.0015427841193127155,
0.002137490961350199,
0.004271426133197859
],
"target": 0,
"brier": 8.842368385453817e-05,
"nll": 0.007983484590021664
},
{
"id": "transfer-v4-0420",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7875997923899002,
"probabilities": [
0.0014264260942844279,
0.0020305511759119254,
0.20894323033990347,
0.7875997923899002
],
"target": 3,
"brier": 0.08877727952716791,
"nll": 0.2387651958156013
},
{
"id": "transfer-v4-0421",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9918654766576428,
"probabilities": [
0.002670236685697703,
0.9918654766576428,
0.0025027706806423585,
0.00296151597601709
],
"target": 1,
"brier": 8.833507192108752e-05,
"nll": 0.008167789100910018
},
{
"id": "transfer-v4-0422",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": false,
"confidence": 0.5538114268048746,
"probabilities": [
0.40350240168346163,
0.024698991144456034,
0.5538114268048746,
0.017987180367207672
],
"target": 0,
"brier": 0.6634500600781658,
"nll": 0.9075728391623092
},
{
"id": "transfer-v4-0423",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9757868369599239,
"probabilities": [
0.9757868369599239,
0.004308289057379697,
0.012684395950244608,
0.007220478032451804
],
"target": 0,
"brier": 0.0008178678226469481,
"nll": 0.02451112117701252
},
{
"id": "transfer-v4-0424",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9954944299691869,
"probabilities": [
0.0014917435232682118,
0.0007240562300194691,
0.9954944299691869,
0.0022897702775254015
],
"target": 2,
"brier": 2.8292765389842474e-05,
"nll": 0.004515750702794048
},
{
"id": "transfer-v4-0425",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.6642611301116843,
"probabilities": [
0.2471426009652994,
0.6642611301116843,
0.04481560892387138,
0.0437806599991449
],
"target": 1,
"brier": 0.1777252389589547,
"nll": 0.409079938574901
},
{
"id": "transfer-v4-0426",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.909264877313553,
"probabilities": [
0.0004191826240248232,
0.005367963310175987,
0.08494797675224625,
0.909264877313553
],
"target": 3,
"brier": 0.015478011987396439,
"nll": 0.09511883306737115
},
{
"id": "transfer-v4-0427",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9901204371996526,
"probabilities": [
0.001504908821443004,
0.0030187923331145023,
0.9901204371996526,
0.00535586164578987
],
"target": 2,
"brier": 0.00013766887280617916,
"nll": 0.009928689515694398
},
{
"id": "transfer-v4-0428",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9724022064606975,
"probabilities": [
0.003304649145645231,
0.9724022064606975,
0.013529422676107794,
0.010763721717549433
],
"target": 1,
"brier": 0.0010714618973754041,
"nll": 0.02798576745523025
},
{
"id": "transfer-v4-0429",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9807259865282263,
"probabilities": [
0.0013255517824121287,
0.9807259865282263,
0.0036652117894237952,
0.014283249899937778
],
"target": 1,
"brier": 0.0005906896880033741,
"nll": 0.01946217899648845
},
{
"id": "transfer-v4-0430",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9827813316204468,
"probabilities": [
0.9827813316204468,
0.0030718801415138756,
0.007737981005978672,
0.006408807232060702
],
"target": 0,
"brier": 0.0004068681485554533,
"nll": 0.0173686336107126
},
{
"id": "transfer-v4-0431",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": false,
"confidence": 0.6183788546033631,
"probabilities": [
0.24989441596364914,
0.08760866941479335,
0.04411806001819447,
0.6183788546033631
],
"target": 0,
"brier": 0.9546724771994818,
"nll": 1.3867167864743222
},
{
"id": "transfer-v4-0432",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9959885833111479,
"probabilities": [
0.003097562229799623,
0.0003900200092982999,
0.0005238344497541315,
0.9959885833111479
],
"target": 3,
"brier": 2.611287375748443e-05,
"nll": 0.00401948400224233
},
{
"id": "transfer-v4-0433",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9652216677190596,
"probabilities": [
0.9652216677190596,
0.01046826251097311,
0.010142444887986417,
0.014167624881980822
],
"target": 0,
"brier": 0.0016227076993445104,
"nll": 0.03539749654098422
},
{
"id": "transfer-v4-0434",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9259845355716199,
"probabilities": [
0.024745240116159244,
0.9259845355716199,
0.04402598615663165,
0.0052442381555893045
],
"target": 1,
"brier": 0.008056405373851643,
"nll": 0.07689774472203915
},
{
"id": "transfer-v4-0435",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9838933530066403,
"probabilities": [
0.9838933530066403,
0.009258141350996778,
0.0030092276761610505,
0.0038392779662019313
],
"target": 0,
"brier": 0.0003689327651524777,
"nll": 0.016237768894351183
},
{
"id": "transfer-v4-0436",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.45919323309654914,
"probabilities": [
0.45919323309654914,
0.3975804179726572,
0.07571987864166407,
0.06750647028912954
],
"target": 0,
"brier": 0.4608327714362817,
"nll": 0.7782841703733633
},
{
"id": "transfer-v4-0437",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.997023397434881,
"probabilities": [
0.997023397434881,
0.0015801445016942765,
0.0007510145613714961,
0.0006454435020532427
],
"target": 0,
"brier": 1.233763966264245e-05,
"nll": 0.0029810414572679464
},
{
"id": "transfer-v4-0438",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7377458975705332,
"probabilities": [
0.16155554715295614,
0.048463949154256634,
0.052234606122253974,
0.7377458975705332
],
"target": 3,
"brier": 0.09995461750134967,
"nll": 0.3041558259057817
},
{
"id": "transfer-v4-0439",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9617147821858719,
"probabilities": [
0.000994931945379024,
0.9617147821858719,
0.026906850868917757,
0.010383434999831272
],
"target": 1,
"brier": 0.002298542138729067,
"nll": 0.03903735649083478
},
{
"id": "transfer-v4-0440",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.977204219532268,
"probabilities": [
0.01227679682415346,
0.977204219532268,
0.005307469137833184,
0.005211514505745381
],
"target": 1,
"brier": 0.0007256964594872229,
"nll": 0.023059621625610503
},
{
"id": "transfer-v4-0441",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9848274865907103,
"probabilities": [
0.0028700536585092875,
0.0029411203207411513,
0.9848274865907103,
0.00936133943003924
],
"target": 2,
"brier": 0.0003347272358232826,
"nll": 0.015288793665984918
},
{
"id": "transfer-v4-0442",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9512385457715263,
"probabilities": [
0.01841900374880353,
0.9512385457715263,
0.02784391588552379,
0.00249853459414633
],
"target": 1,
"brier": 0.003498465444532241,
"nll": 0.049990411117606263
},
{
"id": "transfer-v4-0443",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.956471167868017,
"probabilities": [
0.007459497722068049,
0.014643200089597705,
0.956471167868017,
0.02142613432031723
],
"target": 2,
"brier": 0.002623905873816164,
"nll": 0.04450463392466328
},
{
"id": "transfer-v4-0444",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.994022256588761,
"probabilities": [
0.000942880757841453,
0.994022256588761,
0.0019944819083730606,
0.0030403807450245617
],
"target": 1,
"brier": 4.984431357166277e-05,
"nll": 0.005995681641869065
},
{
"id": "transfer-v4-0445",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.978474068488198,
"probabilities": [
0.978474068488198,
0.003711182811136197,
0.006363330330407129,
0.011451418370258721
],
"target": 0,
"brier": 0.0006487655608930431,
"nll": 0.02176099378669838
},
{
"id": "transfer-v4-0446",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.917709357200209,
"probabilities": [
0.023604963474434117,
0.028581924948767434,
0.030103754376589534,
0.917709357200209
],
"target": 3,
"brier": 0.009052106654375176,
"nll": 0.08587454284845804
},
{
"id": "transfer-v4-0447",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9923494494072101,
"probabilities": [
0.0006759594392205837,
0.0022439247960488852,
0.004730666357520327,
0.9923494494072101
],
"target": 3,
"brier": 8.640224821280622e-05,
"nll": 0.0076799661813185295
},
{
"id": "transfer-v4-0448",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9925623597928889,
"probabilities": [
0.0024663428929575424,
0.0008595802991170839,
0.9925623597928889,
0.004111717015036482
],
"target": 2,
"brier": 7.904643421844899e-05,
"nll": 0.007465437368997059
},
{
"id": "transfer-v4-0449",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9865345155554797,
"probabilities": [
0.9865345155554797,
0.00898302925608722,
0.0022074762340165374,
0.0022749789544165423
],
"target": 0,
"brier": 0.0002720625665081241,
"nll": 0.013556966239507074
},
{
"id": "transfer-v4-0450",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8987908681426691,
"probabilities": [
0.05362287726036211,
0.8987908681426691,
0.03051101338064159,
0.017075241216327218
],
"target": 1,
"brier": 0.01434118713710391,
"nll": 0.10670489877746199
},
{
"id": "transfer-v4-0451",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9940715881759314,
"probabilities": [
0.0030523186067382083,
0.0025824942862730277,
0.00029359893105728374,
0.9940715881759314
],
"target": 3,
"brier": 5.121819270374697e-05,
"nll": 0.005946054621182395
},
{
"id": "transfer-v4-0452",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.985435197518171,
"probabilities": [
0.001490856561748939,
0.0036489610109364102,
0.985435197518171,
0.009424984909143714
],
"target": 2,
"brier": 0.0003165013816193231,
"nll": 0.0146719104943815
},
{
"id": "transfer-v4-0453",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9818852651278971,
"probabilities": [
0.0029313662410188034,
0.0035479308959917985,
0.9818852651278971,
0.011635437735092262
],
"target": 2,
"brier": 0.0004847077524555081,
"nll": 0.018280815409055046
},
{
"id": "transfer-v4-0454",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9959211165649186,
"probabilities": [
0.0015192399452330447,
0.0024414304193203207,
0.00011821307052809746,
0.9959211165649186
],
"target": 3,
"brier": 2.491993691059982e-05,
"nll": 0.004087224770068672
},
{
"id": "transfer-v4-0455",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.951894684569813,
"probabilities": [
0.011561130911018368,
0.951894684569813,
0.028371665151147196,
0.008172519368021424
],
"target": 1,
"brier": 0.003319522576849001,
"nll": 0.04930087576209549
},
{
"id": "transfer-v4-0456",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9851378321710897,
"probabilities": [
0.0053222603808989605,
0.9851378321710897,
0.002381901751239526,
0.007158005696771735
],
"target": 1,
"brier": 0.00030612098964435627,
"nll": 0.014973716461334486
},
{
"id": "transfer-v4-0457",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9837703079522369,
"probabilities": [
0.0062709488645268045,
0.0022906056546291003,
0.9837703079522369,
0.007668137528607262
],
"target": 2,
"brier": 0.00036677491104939017,
"nll": 0.01636283605598575
},
{
"id": "transfer-v4-0458",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9858178186497173,
"probabilities": [
0.0035990244974688844,
0.9858178186497173,
0.005324266683595254,
0.005258890169218608
],
"target": 1,
"brier": 0.00027009098671563434,
"nll": 0.014283709554965619
},
{
"id": "transfer-v4-0459",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9708094737003994,
"probabilities": [
0.9708094737003994,
0.010188220215884423,
0.006253286820767397,
0.012749019262948818
],
"target": 0,
"brier": 0.0011575277450448546,
"nll": 0.029625046524237083
},
{
"id": "transfer-v4-0460",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9799688955846287,
"probabilities": [
0.9799688955846287,
0.003519060501632092,
0.003542502823347602,
0.012969541090391567
],
"target": 0,
"brier": 0.0005943872532624341,
"nll": 0.02023444702057692
},
{
"id": "transfer-v4-0461",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9935793549307904,
"probabilities": [
0.0013533826704361365,
0.002195502326203608,
0.0028717600725698166,
0.9935793549307904
],
"target": 3,
"brier": 5.6123564136173856e-05,
"nll": 0.00644134606751078
},
{
"id": "transfer-v4-0462",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9723070186326477,
"probabilities": [
0.0005890187411164185,
0.022186601357559885,
0.004917361268675974,
0.9723070186326477
],
"target": 3,
"brier": 0.001283673881735862,
"nll": 0.028083661605057503
},
{
"id": "transfer-v4-0463",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9835267441848617,
"probabilities": [
0.9835267441848617,
0.0083733851905715,
0.004100144779882717,
0.003999725844684001
],
"target": 0,
"brier": 0.00037429073074930107,
"nll": 0.01661044865557255
},
{
"id": "transfer-v4-0464",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9937445292294239,
"probabilities": [
0.9937445292294239,
0.0015716866693466483,
0.0006996844733905133,
0.003984099627838968
],
"target": 0,
"brier": 5.796372175498412e-05,
"nll": 0.006275118206687145
},
{
"id": "transfer-v4-0465",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9698695820333106,
"probabilities": [
0.9698695820333106,
0.01733784321059984,
0.005998035697330488,
0.006794539058759001
],
"target": 0,
"brier": 0.0012905850872901923,
"nll": 0.03059366803617423
},
{
"id": "transfer-v4-0466",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9697661305008974,
"probabilities": [
0.9697661305008974,
0.009067653589686041,
0.004994280121810789,
0.01617193578760575
],
"target": 0,
"brier": 0.0012827835475648682,
"nll": 0.030700339131001758
},
{
"id": "transfer-v4-0467",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.6594803492971594,
"probabilities": [
0.0095803963477633,
0.01978586475777671,
0.6594803492971594,
0.31115338959730054
],
"target": 2,
"brier": 0.21325332881106737,
"nll": 0.41630310363387496
},
{
"id": "transfer-v4-0468",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9832767669397697,
"probabilities": [
0.9832767669397697,
0.005315584358309284,
0.0019838475540811078,
0.009423801147839849
],
"target": 0,
"brier": 0.0004006656402489422,
"nll": 0.016864645117012786
},
{
"id": "transfer-v4-0469",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9559474502862424,
"probabilities": [
0.9559474502862424,
0.0030031434460264976,
0.0034758008243328817,
0.03757360544339823
],
"target": 0,
"brier": 0.0033735030242270955,
"nll": 0.045052335761379354
},
{
"id": "transfer-v4-0470",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.858316316236836,
"probabilities": [
0.858316316236836,
0.04657213043853268,
0.019435321714775262,
0.07567623160985607
],
"target": 0,
"brier": 0.02834785333910935,
"nll": 0.1527825804924349
},
{
"id": "transfer-v4-0471",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7235892179534055,
"probabilities": [
0.002780632720108936,
0.7235892179534055,
0.26187683456615607,
0.011753314760329519
],
"target": 1,
"brier": 0.14512826924017938,
"nll": 0.32353142613391656
},
{
"id": "transfer-v4-0472",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7160923125029758,
"probabilities": [
0.7160923125029758,
0.05374853120646172,
0.05082784763518955,
0.17933130865537292
],
"target": 0,
"brier": 0.11823566798603462,
"nll": 0.3339461922552198
},
{
"id": "transfer-v4-0473",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9702728871526389,
"probabilities": [
0.0020686730031151505,
0.9702728871526389,
0.018121430435172992,
0.00953700940907293
],
"target": 1,
"brier": 0.0013073214357191166,
"nll": 0.030177920088234448
},
{
"id": "transfer-v4-0474",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9906939279865125,
"probabilities": [
0.0008553400927647283,
0.002012526507093742,
0.9906939279865125,
0.006438205413629098
],
"target": 2,
"brier": 0.00013283533488434482,
"nll": 0.009349644035246308
},
{
"id": "transfer-v4-0475",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9264005609167852,
"probabilities": [
0.0012700991029533494,
0.001167092379404579,
0.9264005609167852,
0.0711622476008568
],
"target": 2,
"brier": 0.010483918173322879,
"nll": 0.07644856668346732
},
{
"id": "transfer-v4-0476",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9784072016453186,
"probabilities": [
0.9784072016453186,
0.0023887702202712016,
0.0035278426858581908,
0.015676185448552007
],
"target": 0,
"brier": 0.000730143628184744,
"nll": 0.02182933400122845
},
{
"id": "transfer-v4-0477",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.993353280715998,
"probabilities": [
0.002226241007063646,
0.0003885731696071949,
0.993353280715998,
0.004031905107331097
],
"target": 2,
"brier": 6.55422741645164e-05,
"nll": 0.006668907094706214
},
{
"id": "transfer-v4-0478",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9301914194788777,
"probabilities": [
0.0014156015247519906,
0.9301914194788777,
0.06138411659944608,
0.007008862396924177
],
"target": 1,
"brier": 0.008692375764844301,
"nll": 0.07236488661774514
},
{
"id": "transfer-v4-0479",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9917703900441226,
"probabilities": [
0.9917703900441226,
0.0009353539239528197,
0.00596911322478022,
0.0013251428071443389
],
"target": 0,
"brier": 0.00010598768313850292,
"nll": 0.008263660137715916
},
{
"id": "transfer-v4-0480",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3110891259380495,
"probabilities": [
0.30222975982554434,
0.14011332288300005,
0.3110891259380495,
0.12146719454625848,
0.12510059680714758
],
"target": 0,
"brier": 0.6336959342717761,
"nll": 1.1965677567400974
},
{
"id": "transfer-v4-0481",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.36044553754058256,
"probabilities": [
0.2589087033922253,
0.1892616188966263,
0.36044553754058256,
0.19138414017056582
],
"target": 2,
"brier": 0.5485114766401962,
"nll": 1.0204144084534827
},
{
"id": "transfer-v4-0482",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.29635678066418086,
"probabilities": [
0.25923938718018175,
0.29635678066418086,
0.22861557730803983,
0.21578825484759756
],
"target": 1,
"brier": 0.6611484931008919,
"nll": 1.2161912104155441
},
{
"id": "transfer-v4-0483",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9429950815108078,
"probabilities": [
0.0009831753664710716,
0.9429950815108078,
0.00654007920549336,
0.04423281597781683,
0.005248847939410947
],
"target": 1,
"brier": 0.005277392415793275,
"nll": 0.05869421215145702
},
{
"id": "transfer-v4-0484",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9433025352300066,
"probabilities": [
0.025084354596644928,
0.9433025352300066,
0.0033916810890954256,
0.028221429084253045
],
"target": 1,
"brier": 0.004651779917042513,
"nll": 0.058368225711997124
},
{
"id": "transfer-v4-0485",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9819097685812538,
"probabilities": [
0.9819097685812538,
0.008702888301413237,
0.002884497682230624,
0.006502845435102404
],
"target": 0,
"brier": 0.0004536040632022941,
"nll": 0.018255860204527734
},
{
"id": "transfer-v4-0486",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7721177073490292,
"probabilities": [
0.7721177073490292,
0.19579450111426736,
0.010089970777436235,
0.009956080123432945,
0.012041740635834259
],
"target": 0,
"brier": 0.09061176052970199,
"nll": 0.25861826992046627
},
{
"id": "transfer-v4-0487",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8129495482811318,
"probabilities": [
0.08342074572547209,
0.0502254223644164,
0.05340428362897979,
0.8129495482811318
],
"target": 3,
"brier": 0.04732150286723507,
"nll": 0.20708622759466455
},
{
"id": "transfer-v4-0488",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9457581847781686,
"probabilities": [
0.9457581847781686,
0.017159962323458545,
0.016612508584791442,
0.020469344313581335
],
"target": 0,
"brier": 0.003931608323609527,
"nll": 0.05576836123399742
},
{
"id": "transfer-v4-0489",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.5171185318850952,
"probabilities": [
0.3761965169529129,
0.060296202349714646,
0.03068762753729694,
0.015701121274980353,
0.5171185318850952
],
"target": 0,
"brier": 0.6613662491916309,
"nll": 0.9776436206564381
},
{
"id": "transfer-v4-0490",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7781986056134,
"probabilities": [
0.15607452508862707,
0.04599509049948372,
0.7781986056134,
0.019731778798489114
],
"target": 2,
"brier": 0.07606000737808874,
"nll": 0.25077351024336364
},
{
"id": "transfer-v4-0491",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7883290986187184,
"probabilities": [
0.7883290986187184,
0.12175119444779581,
0.059994264282040445,
0.029925442651445384
],
"target": 0,
"brier": 0.0641227677056575,
"nll": 0.23783963846965386
},
{
"id": "transfer-v4-0492",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8936252222656096,
"probabilities": [
0.8936252222656096,
0.00640305706568299,
0.006966495595961233,
0.0023264266204214828,
0.09067879845232475
],
"target": 0,
"brier": 0.01963318128829344,
"nll": 0.11246880617157164
},
{
"id": "transfer-v4-0493",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9174120526668624,
"probabilities": [
0.018018973017949205,
0.03496666436263683,
0.02960230995255152,
0.9174120526668624
],
"target": 3,
"brier": 0.009244416804498914,
"nll": 0.0861985590517992
},
{
"id": "transfer-v4-0494",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.982620949601031,
"probabilities": [
0.982620949601031,
0.006973602351137469,
0.007872820314919732,
0.002532627732911841
],
"target": 0,
"brier": 0.00041905802546622265,
"nll": 0.017531838895762063
},
{
"id": "transfer-v4-0495",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.753161893149839,
"probabilities": [
0.003630608896525638,
0.01208544404341688,
0.0641359922156863,
0.1669860616945322,
0.753161893149839
],
"target": 2,
"brier": 1.4711378624381035,
"nll": 2.74674957161348
},
{
"id": "transfer-v4-0496",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.7662971087411335,
"probabilities": [
0.021694066019307953,
0.006573948647246905,
0.20543487659231158,
0.7662971087411335
],
"target": 2,
"brier": 1.2190588435021625,
"nll": 1.5826261974971638
},
{
"id": "transfer-v4-0497",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.847475795140316,
"probabilities": [
0.005079128373212414,
0.1336505700230722,
0.013794506463399359,
0.847475795140316
],
"target": 1,
"brier": 1.468992644123659,
"nll": 2.0125265713627414
},
{
"id": "transfer-v4-0498",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.4635043787756452,
"probabilities": [
0.008549038408360838,
0.44096866701790627,
0.4635043787756452,
0.07535049396460451,
0.011627421833483167
],
"target": 1,
"brier": 0.5332383203368447,
"nll": 0.8187814559054685
},
{
"id": "transfer-v4-0499",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8694172035070837,
"probabilities": [
0.8694172035070837,
0.09970180093797745,
0.019287772764083336,
0.011593222790855508
],
"target": 0,
"brier": 0.027498736843063795,
"nll": 0.13993217283039422
},
{
"id": "transfer-v4-0500",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7930130500655537,
"probabilities": [
0.7930130500655537,
0.15801646393069926,
0.02645145017654643,
0.022519035827200655
],
"target": 0,
"brier": 0.06901958650735604,
"nll": 0.2319156009057063
},
{
"id": "transfer-v4-0501",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.7296552211534371,
"probabilities": [
0.05721713719775622,
0.17254096623128398,
0.017469657942962343,
0.7296552211534371,
0.023117017474560426
],
"target": 4,
"brier": 1.5200464780700456,
"nll": 3.767186245464809
},
{
"id": "transfer-v4-0502",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.795209337833402,
"probabilities": [
0.021439587417846337,
0.795209337833402,
0.09348641959129844,
0.08986465515745322
],
"target": 1,
"brier": 0.059214238113849446,
"nll": 0.2291498809604764
},
{
"id": "transfer-v4-0503",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.5596015590755854,
"probabilities": [
0.5596015590755854,
0.07667464134528447,
0.2855942611281807,
0.07812953845094947
],
"target": 3,
"brier": 1.250442135411265,
"nll": 2.5493870804407033
},
{
"id": "transfer-v4-0504",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8108277146235193,
"probabilities": [
0.09254713902235721,
0.006341895883291641,
0.08887601452389933,
0.001407235946932499,
0.8108277146235193
],
"target": 4,
"brier": 0.05229227240984137,
"nll": 0.2096996831637125
},
{
"id": "transfer-v4-0505",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.48824129783637016,
"probabilities": [
0.48824129783637016,
0.030256929681976453,
0.4751872254353753,
0.006314547046278125
],
"target": 2,
"brier": 0.5147633685573424,
"nll": 0.7440463937963574
},
{
"id": "transfer-v4-0506",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8871570404199799,
"probabilities": [
0.10402503860622926,
0.0023166554810950257,
0.006501265492695812,
0.8871570404199799
],
"target": 3,
"brier": 0.023602375529430144,
"nll": 0.11973326564676645
},
{
"id": "transfer-v4-0507",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.8577861806973651,
"probabilities": [
0.002809177587748476,
0.133284861497819,
0.002207725933330905,
0.8577861806973651,
0.0039120542837364535
],
"target": 3,
"brier": 0.03801769440637039,
"nll": 0.15340041719773856
},
{
"id": "transfer-v4-0508",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9665835299805509,
"probabilities": [
0.9665835299805509,
0.010850689818552093,
0.01173950500463901,
0.010826275196258079
],
"target": 0,
"brier": 0.0014894221504782306,
"nll": 0.033987558842587355
},
{
"id": "transfer-v4-0509",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.9842851308826623,
"probabilities": [
0.00515691353689063,
0.9842851308826623,
0.0041371931296564045,
0.006420762450790629
],
"target": 1,
"brier": 0.0003318934260435778,
"nll": 0.015839656747100805
},
{
"id": "transfer-v4-0510",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.6350894866087234,
"probabilities": [
0.016997678996887013,
0.12238649103727615,
0.6350894866087234,
0.1713420828498007,
0.05418426050731263
],
"target": 4,
"brier": 1.3425315527080375,
"nll": 2.915364809253825
},
{
"id": "transfer-v4-0511",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": true,
"confidence": 0.7408685601405588,
"probabilities": [
0.10831963894904063,
0.10269893591069874,
0.04811286499970185,
0.7408685601405588
],
"target": 3,
"brier": 0.09174416652134706,
"nll": 0.2999320511466906
},
{
"id": "transfer-v4-0512",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.34139080381650344,
"probabilities": [
0.34139080381650344,
0.32398454803159304,
0.14985457732623417,
0.18477007082566935
],
"target": 3,
"brier": 0.9085699000609225,
"nll": 1.6886430872971354
},
{
"id": "transfer-v4-0513",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.291403799163536,
"probabilities": [
0.040814447995966494,
0.291403799163536,
0.2709150602261906,
0.18040540747193468,
0.21646128514237223
],
"target": 3,
"brier": 0.8785677472562511,
"nll": 1.7125486969029924
},
{
"id": "transfer-v4-0514",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.3339990154057521,
"probabilities": [
0.3012116618725284,
0.3339990154057521,
0.061684349067904404,
0.3031049736538151
],
"target": 0,
"brier": 0.6955380677685764,
"nll": 1.1999420657696396
},
{
"id": "transfer-v4-0515",
"question": "answer",
"type": "choice",
"source": "mmlu",
"error": null,
"correct": false,
"confidence": 0.38449663325794264,
"probabilities": [
0.38449663325794264,
0.25210203030021283,
0.06635481419270241,
0.2970465222491421
],
"target": 1,
"brier": 0.7998286318146147,
"nll": 1.37792139126967
},
{
"id": "transfer-v4-0516",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.48337086936061796,
"probabilities": [
0.48337086936061796,
0.09413724208696139,
0.06283069776479588,
0.009340379012547672,
0.014624241679861646,
0.30485876231543796,
0.030837807779777515
],
"target": 1,
"brier": 1.1523733765758393,
"nll": 2.3630015393065396
},
{
"id": "transfer-v4-0517",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5814301317424501,
"probabilities": [
0.5814301317424501,
0.2707494472083687,
0.08146247191855245,
0.021082950559603512,
0.010427962891497064,
0.034847035679528154
],
"target": 0,
"brier": 0.25690968121787633,
"nll": 0.542264466017887
},
{
"id": "transfer-v4-0518",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.503044727275398,
"probabilities": [
0.14568486891138294,
0.21269467591882502,
0.04168997355749816,
0.02474985099257818,
0.503044727275398,
0.07213590334431773
],
"target": 1,
"brier": 0.9016819495665508,
"nll": 1.547897588030339
},
{
"id": "transfer-v4-0519",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.788760798734677,
"probabilities": [
0.04530950735891312,
0.042740550837561564,
0.002049616583323473,
0.0022367632976948546,
0.10449961058969214,
0.01440315259813785,
0.788760798734677
],
"target": 0,
"brier": 1.546541112502096,
"nll": 3.0942383930412287
},
{
"id": "transfer-v4-0520",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8511553064863453,
"probabilities": [
0.00246312808597237,
0.8511553064863453,
0.0017453239296869427,
0.10193969644964727,
0.01293626189429658,
0.029760283154051555
],
"target": 1,
"brier": 0.03360857898021463,
"nll": 0.16116066825077832
},
{
"id": "transfer-v4-0521",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5032401573150199,
"probabilities": [
0.21296751042990691,
0.20107550488343778,
0.009091841793514452,
0.00928446258088328,
0.5032401573150199,
0.06434052299723772
],
"target": 0,
"brier": 0.9174107199696463,
"nll": 1.546615658100008
},
{
"id": "transfer-v4-0522",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.4973698478400955,
"probabilities": [
0.00032645006501242214,
0.4155713552611135,
0.4973698478400955,
0.03359580359805439,
0.0005296326624965294,
0.004677285366893723,
0.04792962520633393
],
"target": 2,
"brier": 0.4287848122444715,
"nll": 0.6984213689916958
},
{
"id": "transfer-v4-0523",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8583398152576639,
"probabilities": [
0.0010494231597647488,
0.8583398152576639,
0.0008398523486053513,
0.08220523125887895,
0.04690515406956335,
0.01066052390552366
],
"target": 1,
"brier": 0.02914085487672399,
"nll": 0.15275520282442295
},
{
"id": "transfer-v4-0524",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.859313200554835,
"probabilities": [
0.0005172107907504972,
0.012806378419473123,
0.859313200554835,
0.059426118816181824,
0.000922637601293423,
0.0670144538174662
],
"target": 2,
"brier": 0.027980298251500498,
"nll": 0.15162181279464523
},
{
"id": "transfer-v4-0525",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4132379944088839,
"probabilities": [
0.0021941546455209317,
0.004987064455233676,
0.17171991350009616,
0.007610323856255986,
0.050602451711329564,
0.4132379944088839,
0.3496480974226797
],
"target": 2,
"brier": 0.9817155440215483,
"nll": 1.7618905393523416
},
{
"id": "transfer-v4-0526",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5275971416290184,
"probabilities": [
0.006777486456033924,
0.5275971416290184,
0.05429387219003104,
0.00705241614609063,
0.39994678832466685,
0.004332295254159142
],
"target": 1,
"brier": 0.38618415832400554,
"nll": 0.6394222758393652
},
{
"id": "transfer-v4-0527",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.6292385738539668,
"probabilities": [
0.003634276617084688,
0.008258077831998278,
0.2673923536770166,
0.012287220299700372,
0.07918949772023327,
0.6292385738539668
],
"target": 2,
"brier": 0.9391585024245604,
"nll": 1.3190382097978735
},
{
"id": "transfer-v4-0528",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6211348200045448,
"probabilities": [
0.3548698737052529,
0.6211348200045448,
0.020068891424137474,
0.00039642307245883474,
0.000507087739750355,
0.0004879080243668218,
0.0025349960294888145
],
"target": 1,
"brier": 0.2698812908279026,
"nll": 0.47620711915517533
},
{
"id": "transfer-v4-0529",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9433570067100123,
"probabilities": [
0.04470672996327298,
0.0052555694603691055,
0.0010873069482915843,
0.003387651947759386,
0.0022057349702945773,
0.9433570067100123
],
"target": 5,
"brier": 0.005252265092089505,
"nll": 0.058310481875539145
},
{
"id": "transfer-v4-0530",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9750382258787834,
"probabilities": [
0.9750382258787834,
0.0010041416343108676,
0.0172091088387691,
0.001064905658993378,
0.0009847836290263403,
0.004698834360116933
],
"target": 0,
"brier": 0.0009444347619273651,
"nll": 0.025278602723304712
},
{
"id": "transfer-v4-0531",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.40687112308444284,
"probabilities": [
0.40687112308444284,
0.019512180856814748,
0.01427201413106963,
0.33071083877623875,
0.09028273361698999,
0.010824092075246507,
0.12752701745919753
],
"target": 4,
"brier": 1.1194639911798938,
"nll": 2.404809048171429
},
{
"id": "transfer-v4-0532",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.44755282581268974,
"probabilities": [
0.02431875258387297,
0.44755282581268974,
0.37044202936401566,
0.12870581328211525,
0.018239324742561906,
0.01074125421474451
],
"target": 1,
"brier": 0.46002981299589135,
"nll": 0.8039607017253639
},
{
"id": "transfer-v4-0533",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.32492398973611003,
"probabilities": [
0.32492398973611003,
0.05540126148312344,
0.05908365503636259,
0.21596354085234148,
0.03389370043654963,
0.31073385245551277
],
"target": 3,
"brier": 0.8245532564363339,
"nll": 1.5326456778952748
},
{
"id": "transfer-v4-0534",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.37278887889899,
"probabilities": [
0.33353433245933384,
0.00279385598465234,
0.37278887889899,
0.24998235877125308,
0.034435082467517926,
0.003945076400030472,
0.0025204150182223995
],
"target": 3,
"brier": 0.8139586579696665,
"nll": 1.386364928524699
},
{
"id": "transfer-v4-0535",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.48539448010453246,
"probabilities": [
0.4550025484291955,
0.0038446118302858053,
0.0031597935741757674,
0.48539448010453246,
0.04698721713846185,
0.005611348923348584
],
"target": 0,
"brier": 0.5348940746813342,
"nll": 0.787452259103585
},
{
"id": "transfer-v4-0536",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4881672167670805,
"probabilities": [
0.058047602680512095,
0.0077009562759473155,
0.4881672167670805,
0.43202175845163227,
0.008927721355592694,
0.005134744469235061
],
"target": 3,
"brier": 0.5644414131123798,
"nll": 0.8392793252202049
},
{
"id": "transfer-v4-0537",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.4937820372241998,
"probabilities": [
0.4937820372241998,
0.004163736173633706,
0.008504776594760849,
0.031027663097429752,
0.00023034652760270058,
0.00021063780795741176,
0.4620808025744158
],
"target": 6,
"brier": 0.5342302444732125,
"nll": 0.7720155058459358
},
{
"id": "transfer-v4-0538",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9285914152691123,
"probabilities": [
0.9285914152691123,
0.01427694107752551,
0.006177100719367165,
0.0503466605502368,
0.00031106656616004347,
0.00029681581759818563
],
"target": 0,
"brier": 0.007876144683695645,
"nll": 0.07408644824939571
},
{
"id": "transfer-v4-0539",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8963593789989327,
"probabilities": [
0.01452593776577758,
0.06387072765527639,
0.024143596974787716,
0.0005530802851048771,
0.0005472783201207641,
0.8963593789989327
],
"target": 5,
"brier": 0.015615369726919029,
"nll": 0.10941385379061705
},
{
"id": "transfer-v4-0540",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.3772912353113365,
"probabilities": [
0.19182588335849682,
0.0029681034169864316,
0.3772912353113365,
0.37102651838047696,
0.0209018699350761,
0.0033054431511392573,
0.03268094644648792
],
"target": 2,
"brier": 0.5637487205076277,
"nll": 0.9747378823073057
},
{
"id": "transfer-v4-0541",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6648502945899963,
"probabilities": [
0.0023380229249596596,
0.006699248217046261,
0.2314067780971527,
0.6648502945899963,
0.04138314723968506,
0.05332250893115997
],
"target": 3,
"brier": 0.17048062309776343,
"nll": 0.408193384587099
},
{
"id": "transfer-v4-0542",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5821732060703926,
"probabilities": [
0.30523528630028923,
0.004675515762167599,
0.5821732060703926,
0.047096333698972155,
0.006524565583276586,
0.05429509258490185
],
"target": 2,
"brier": 0.2729782618586949,
"nll": 0.5409872705943167
},
{
"id": "transfer-v4-0543",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5741970191497298,
"probabilities": [
0.03495119673029726,
0.058988314276337224,
0.09803361597267442,
0.002308267960290036,
0.001229875646585676,
0.5741970191497298,
0.23029171026408563
],
"target": 6,
"brier": 0.9364717060184258,
"nll": 1.4684084681829142
},
{
"id": "transfer-v4-0544",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.6987431904673947,
"probabilities": [
0.1630666326371038,
0.06253526058401937,
0.07174396169115788,
0.002581619765983128,
0.6987431904673947,
0.0013293348543410388
],
"target": 4,
"brier": 0.12641267871659317,
"nll": 0.35847199986636796
},
{
"id": "transfer-v4-0545",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.5448612060981248,
"probabilities": [
0.10108379434647458,
0.16668767000892237,
0.006413244278193593,
0.004030196525634584,
0.17692388874265003,
0.5448612060981248
],
"target": 5,
"brier": 0.27651346912096597,
"nll": 0.6072241844620835
},
{
"id": "transfer-v4-0546",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.5838966986067711,
"probabilities": [
0.061712652660368426,
0.30868175733606945,
0.01918268210434826,
0.5838966986067711,
0.0008311548764974166,
0.024211682463804084,
0.0014833719521413044
],
"target": 1,
"brier": 0.8236217908534327,
"nll": 1.1754444443414611
},
{
"id": "transfer-v4-0547",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8131692237569732,
"probabilities": [
0.001579484519037542,
0.8131692237569732,
0.058778609420733645,
0.0022628005842835015,
0.0176487145836726,
0.10656116713529952
],
"target": 1,
"brier": 0.05003503838253039,
"nll": 0.20681604379142063
},
{
"id": "transfer-v4-0548",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.7370936168125355,
"probabilities": [
0.7370936168125355,
0.046184770096220136,
0.1502813377144181,
0.0031586130625023486,
0.058986595911633,
0.004295066402690923
],
"target": 0,
"brier": 0.09734512270391403,
"nll": 0.3050403706907108
},
{
"id": "transfer-v4-0549",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": false,
"confidence": 0.6703260043241406,
"probabilities": [
0.001562543934779304,
0.020920198717613827,
0.005094238631645458,
0.6703260043241406,
0.004037419858937489,
0.019339449987370836,
0.2787201445455125
],
"target": 6,
"brier": 0.9704379445677142,
"nll": 1.2775470667133957
},
{
"id": "transfer-v4-0550",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.9186508281240484,
"probabilities": [
0.0022928725459490213,
0.0030502978400787986,
0.007900029098963111,
0.9186508281240484,
0.030678779499422198,
0.03742719289153843
],
"target": 3,
"brier": 0.009036642085407326,
"nll": 0.08484917645917325
},
{
"id": "transfer-v4-0551",
"question": "emotion",
"type": "choice",
"source": "emotion",
"error": null,
"correct": true,
"confidence": 0.8415155144300988,
"probabilities": [
0.004314776373372975,
0.05993658114425488,
0.014610250017839948,
0.07031805590650635,
0.009304822127927138,
0.8415155144300988
],
"target": 5,
"brier": 0.03397301132765701,
"nll": 0.17255082888415388
},
{
"id": "transfer-v4-0552",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9218182542855553,
"probabilities": [
0.002791757223378021,
0.072965107692543,
0.0016402645232173197,
0.0007846162753063233,
0.9218182542855553
],
"target": 4,
"brier": 0.011447392302342372,
"nll": 0.081407196021815
},
{
"id": "transfer-v4-0553",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9192289864142628,
"probabilities": [
0.9192289864142628,
0.033067349898826606,
0.009479260231020567,
0.03822440345589003
],
"target": 0,
"brier": 0.009168367659084842,
"nll": 0.08422001855155341
},
{
"id": "transfer-v4-0554",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9919869712668135,
"probabilities": [
0.0028476328051979054,
0.003907784745904952,
0.0012576111820837236,
0.9919869712668135
],
"target": 3,
"brier": 8.917000957774191e-05,
"nll": 0.008045305587128881
},
{
"id": "transfer-v4-0555",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.4825811142017817,
"probabilities": [
0.3307220972782608,
0.06904812979379442,
0.07472451114719188,
0.04292414757897125,
0.4825811142017817
],
"target": 4,
"brier": 0.3892932882483898,
"nll": 0.7286062599970927
},
{
"id": "transfer-v4-0556",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.628505523290444,
"probabilities": [
0.0974303998244524,
0.11347590302321386,
0.16058817386188973,
0.628505523290444
],
"target": 3,
"brier": 0.18616617118688988,
"nll": 0.4644104629388284
},
{
"id": "transfer-v4-0557",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7381781550701925,
"probabilities": [
0.06947908188139221,
0.07892129903697152,
0.11342146401144379,
0.7381781550701925
],
"target": 3,
"brier": 0.0924710212417117,
"nll": 0.30357008098043176
},
{
"id": "transfer-v4-0558",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9617102599297915,
"probabilities": [
0.00037639156244048905,
0.002002911503738541,
0.0004288818074378548,
0.03548155519659159,
0.9617102599297915
],
"target": 4,
"brier": 0.002729382218517739,
"nll": 0.03904205878593999
},
{
"id": "transfer-v4-0559",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9111837301415457,
"probabilities": [
0.005332914270453581,
0.005369179972117059,
0.9111837301415457,
0.07811417561588359
],
"target": 2,
"brier": 0.014047422291907863,
"nll": 0.09301072242830048
},
{
"id": "transfer-v4-0560",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9951581303011184,
"probabilities": [
0.004034022312303822,
0.0002958315582627113,
0.0005120158283150797,
0.9951581303011184
],
"target": 3,
"brier": 4.006671471642183e-05,
"nll": 0.004853629525025284
},
{
"id": "transfer-v4-0561",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8841430821728996,
"probabilities": [
0.001361596324279603,
0.025051514471282413,
0.0024432480169033766,
0.08700055901463496,
0.8841430821728996
],
"target": 4,
"brier": 0.02162732445998174,
"nll": 0.12313637178038052
},
{
"id": "transfer-v4-0562",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8125624694515134,
"probabilities": [
0.010083516175316257,
0.01966326506651596,
0.15769074930665433,
0.8125624694515134
],
"target": 3,
"brier": 0.060487521566542864,
"nll": 0.20756248225499566
},
{
"id": "transfer-v4-0563",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9699022454904943,
"probabilities": [
0.0017907659640042455,
0.003415994700852022,
0.02489099384464937,
0.9699022454904943
],
"target": 3,
"brier": 0.0015403122636229282,
"nll": 0.03055999040798798
},
{
"id": "transfer-v4-0564",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8870824536002989,
"probabilities": [
0.0015888896137955019,
0.06816405485621951,
0.8870824536002989,
0.041109199421230994,
0.00205540250845509
],
"target": 2,
"brier": 0.01909342618610148,
"nll": 0.11981734315713222
},
{
"id": "transfer-v4-0565",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.5514600744596665,
"probabilities": [
0.5514600744596665,
0.011214499100705164,
0.4283986289892665,
0.008926797450361833
],
"target": 0,
"brier": 0.3849189028264106,
"nll": 0.5951858373612854
},
{
"id": "transfer-v4-0566",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9542409158266313,
"probabilities": [
0.0013006717167661868,
0.04152153794747401,
0.9542409158266313,
0.0029368745091284667
],
"target": 2,
"brier": 0.003828248876706132,
"nll": 0.04683910710173719
},
{
"id": "transfer-v4-0567",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8679451869693523,
"probabilities": [
0.006723431348324863,
0.8679451869693523,
0.009809384971592143,
0.006070726034569988,
0.10945127067616076
],
"target": 1,
"brier": 0.02959633657438887,
"nll": 0.14162671496856694
},
{
"id": "transfer-v4-0568",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9213567852051975,
"probabilities": [
0.9213567852051975,
0.0291096731950199,
0.016331150914881274,
0.0332023906849013
],
"target": 0,
"brier": 0.008401233544179754,
"nll": 0.08190792881182442
},
{
"id": "transfer-v4-0569",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9731404989792327,
"probabilities": [
0.008042356171621188,
0.9731404989792327,
0.011679784644986547,
0.0071373602041595475
],
"target": 1,
"brier": 0.0009734715679129962,
"nll": 0.02722680950287079
},
{
"id": "transfer-v4-0570",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9218049853000085,
"probabilities": [
0.07077902257186289,
0.9218049853000085,
0.0016450690343609324,
0.00271765364057028,
0.003053269453197305
],
"target": 1,
"brier": 0.011143544707951904,
"nll": 0.0814215904873024
},
{
"id": "transfer-v4-0571",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9790604855273906,
"probabilities": [
0.9790604855273906,
0.0063717725543279745,
0.006245224914384416,
0.008322517003897027
],
"target": 0,
"brier": 0.0005873298753441105,
"nll": 0.021161855390360317
},
{
"id": "transfer-v4-0572",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9888811472649972,
"probabilities": [
0.0010607521729085777,
0.9888811472649972,
0.0044692269396360155,
0.0055888736224581695
],
"target": 1,
"brier": 0.00017596357912078636,
"nll": 0.011181129237198734
},
{
"id": "transfer-v4-0573",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9117852505503762,
"probabilities": [
0.00048077566844603877,
0.0866185935698797,
0.0009434105688249539,
0.00017196964247313435,
0.9117852505503762
],
"target": 4,
"brier": 0.015285773514786586,
"nll": 0.09235078752317336
},
{
"id": "transfer-v4-0574",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9936776247094581,
"probabilities": [
0.9936776247094581,
0.004277354352372551,
0.00114646827504126,
0.0008985526631281566
],
"target": 0,
"brier": 6.038997596430616e-05,
"nll": 0.006342446146912127
},
{
"id": "transfer-v4-0575",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9980192931263132,
"probabilities": [
0.0013746781592670124,
0.00028921860376803323,
0.00031681011065171625,
0.9980192931263132
],
"target": 3,
"brier": 5.996955808012516e-06,
"nll": 0.001982671067636722
},
{
"id": "transfer-v4-0576",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8705742983704424,
"probabilities": [
0.04261873757158254,
0.07206122107404705,
0.8705742983704424,
0.007309531316471107,
0.0074362116674568345
],
"target": 2,
"brier": 0.02386891510921106,
"nll": 0.13860217204283204
},
{
"id": "transfer-v4-0577",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.739129849588087,
"probabilities": [
0.06673475429491797,
0.14046159543612893,
0.0536738006808661,
0.739129849588087
],
"target": 3,
"brier": 0.09511709947872926,
"nll": 0.30228166360701164
},
{
"id": "transfer-v4-0578",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.971561619180039,
"probabilities": [
0.0059173322894337825,
0.971561619180039,
0.014250657702645138,
0.008270390827882028
],
"target": 1,
"brier": 0.0011152369344885741,
"nll": 0.028850585330914474
},
{
"id": "transfer-v4-0579",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9135610878136878,
"probabilities": [
0.01731692147304225,
0.004394644140580262,
0.9135610878136878,
0.0064688327880323,
0.05825851378465739
],
"target": 2,
"brier": 0.011226774432415472,
"nll": 0.09040503313535242
},
{
"id": "transfer-v4-0580",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.7672106556348396,
"probabilities": [
0.17109211968334098,
0.040072373082261165,
0.7672106556348396,
0.021624851599558275
],
"target": 2,
"brier": 0.08553682155884676,
"nll": 0.2649938665171288
},
{
"id": "transfer-v4-0581",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9696230978669887,
"probabilities": [
0.018640726978338573,
0.004741563971541486,
0.9696230978669887,
0.006994611183131218
],
"target": 2,
"brier": 0.0013416398999789075,
"nll": 0.030847841893289853
},
{
"id": "transfer-v4-0582",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9139423986315018,
"probabilities": [
0.06422294271449518,
0.003942712892897074,
0.9139423986315018,
0.0009244695537956125,
0.016967476207310293
],
"target": 2,
"brier": 0.011834792001966018,
"nll": 0.08998773070482276
},
{
"id": "transfer-v4-0583",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.6376065744708173,
"probabilities": [
0.6376065744708173,
0.03648733082598839,
0.0027871930809681674,
0.3231189016222262
],
"target": 0,
"brier": 0.23707391320840493,
"nll": 0.45003384028134835
},
{
"id": "transfer-v4-0584",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9581129109926632,
"probabilities": [
0.9581129109926632,
0.008775434598767362,
0.001299950897308669,
0.031811703511260774
],
"target": 0,
"brier": 0.002845210830529577,
"nll": 0.0427896467949137
},
{
"id": "transfer-v4-0585",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.8807242830545324,
"probabilities": [
0.0026842044703782753,
0.10865361635603722,
0.00038184669315494536,
0.00755604942589711,
0.8807242830545324
],
"target": 4,
"brier": 0.02609674964356269,
"nll": 0.1270106611033144
},
{
"id": "transfer-v4-0586",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.9266214463007385,
"probabilities": [
0.01636356026379128,
0.9266214463007385,
0.05558990012383049,
0.0014250933116396684
],
"target": 1,
"brier": 0.008744446134226461,
"nll": 0.07621016111230937
},
{
"id": "transfer-v4-0587",
"question": "answer",
"type": "choice",
"source": "sciq",
"error": null,
"correct": true,
"confidence": 0.985452850466264,
"probabilities": [
0.003368860177900586,
0.0004893677057612875,
0.010688921650074196,
0.985452850466264
],
"target": 3,
"brier": 0.0003374613052479879,
"nll": 0.014653996794908315
},
{
"id": "transfer-v4-0588",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9933390021324158,
"probabilities": [
0.0066609978675842285,
0.9933390021324158
],
"target": 1,
"brier": 8.873778518392328e-05,
"nll": 0.006683281322366721
},
{
"id": "transfer-v4-0589",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.994074500631541,
"probabilities": [
0.994074500631541,
0.005925499368458986
],
"target": 0,
"brier": 7.022308553121569e-05,
"nll": 0.00594312480065666
},
{
"id": "transfer-v4-0590",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9898899793624878,
"probabilities": [
0.010110020637512207,
0.9898899793624878
],
"target": 1,
"brier": 0.00020442503458184547,
"nll": 0.010161473986197964
},
{
"id": "transfer-v4-0591",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9918179120868444,
"probabilities": [
0.9918179120868444,
0.008182087913155556
],
"target": 0,
"brier": 0.00013389312523721247,
"nll": 0.008215744909863557
},
{
"id": "transfer-v4-0592",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9923345446586609,
"probabilities": [
0.007665455341339111,
0.9923345446586609
],
"target": 1,
"brier": 0.00011751841118012862,
"nll": 0.0076949859513112395
},
{
"id": "transfer-v4-0593",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9929880555719137,
"probabilities": [
0.9929880555719137,
0.007011944428086281
],
"target": 0,
"brier": 9.833472932514048e-05,
"nll": 0.0070366436377946725
},
{
"id": "transfer-v4-0594",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9950569868087769,
"probabilities": [
0.0049430131912231445,
0.9950569868087769
],
"target": 1,
"brier": 4.886675881721203e-05,
"nll": 0.004955270288939823
},
{
"id": "transfer-v4-0595",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.997118549188599,
"probabilities": [
0.997118549188599,
0.0028814508114010096
],
"target": 0,
"brier": 1.6605517557047073e-05,
"nll": 0.0028856101827277178
},
{
"id": "transfer-v4-0596",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9931426048278809,
"probabilities": [
0.006857395172119141,
0.9931426048278809
],
"target": 1,
"brier": 9.40477370932058e-05,
"nll": 0.006881015149336651
},
{
"id": "transfer-v4-0597",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9932914329692721,
"probabilities": [
0.9932914329692721,
0.006708567030727863
],
"target": 0,
"brier": 9.000974321153772e-05,
"nll": 0.0067311706150224955
},
{
"id": "transfer-v4-0598",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9907528162002563,
"probabilities": [
0.009247183799743652,
0.9907528162002563
],
"target": 1,
"brier": 0.0001710208164524829,
"nll": 0.009290204422312983
},
{
"id": "transfer-v4-0599",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9935277560725808,
"probabilities": [
0.9935277560725808,
0.006472243927419186
],
"target": 0,
"brier": 8.377988291202905e-05,
"nll": 0.006493279713095837
},
{
"id": "transfer-v4-0600",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9939566850662231,
"probabilities": [
0.0060433149337768555,
0.9939566850662231
],
"target": 1,
"brier": 7.304331077762072e-05,
"nll": 0.006061649667171209
},
{
"id": "transfer-v4-0601",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9959047776646912,
"probabilities": [
0.9959047776646912,
0.00409522233530879
],
"target": 0,
"brier": 3.354169195122396e-05,
"nll": 0.004103630722290743
},
{
"id": "transfer-v4-0602",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9946573376655579,
"probabilities": [
0.005342662334442139,
0.9946573376655579
],
"target": 1,
"brier": 5.7088081639733446e-05,
"nll": 0.005356985393141053
},
{
"id": "transfer-v4-0603",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9956160755828023,
"probabilities": [
0.9956160755828023,
0.004383924417197704
],
"target": 0,
"brier": 3.843758659140446e-05,
"nll": 0.004393561991090164
},
{
"id": "transfer-v4-0604",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.994242250919342,
"probabilities": [
0.005757749080657959,
0.994242250919342
],
"target": 1,
"brier": 6.630334895163514e-05,
"nll": 0.005774388820267021
},
{
"id": "transfer-v4-0605",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9934300263412297,
"probabilities": [
0.9934300263412297,
0.006569973658770323
],
"target": 0,
"brier": 8.63291077538718e-05,
"nll": 0.006591650933959144
},
{
"id": "transfer-v4-0606",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.995023250579834,
"probabilities": [
0.004976749420166016,
0.995023250579834
],
"target": 1,
"brier": 4.9536069582245545e-05,
"nll": 0.004989174679639538
},
{
"id": "transfer-v4-0607",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9967527678236365,
"probabilities": [
0.9967527678236365,
0.003247232176363468
],
"target": 0,
"brier": 2.1089033614420452e-05,
"nll": 0.0032525158761342746
},
{
"id": "transfer-v4-0608",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9946422576904297,
"probabilities": [
0.0053577423095703125,
0.9946422576904297
],
"target": 1,
"brier": 5.741080531151965e-05,
"nll": 0.005372146483168585
},
{
"id": "transfer-v4-0609",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9953621355816722,
"probabilities": [
0.9953621355816722,
0.004637864418327808
],
"target": 0,
"brier": 4.301957272558228e-05,
"nll": 0.004648652680765364
},
{
"id": "transfer-v4-0610",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9954572916030884,
"probabilities": [
0.004542708396911621,
0.9954572916030884
],
"target": 1,
"brier": 4.12723991587427e-05,
"nll": 0.004553057851631902
},
{
"id": "transfer-v4-0611",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9965402593370527,
"probabilities": [
0.9965402593370527,
0.003459740662947297
],
"target": 0,
"brier": 2.3939610909702006e-05,
"nll": 0.0034657394057340963
},
{
"id": "transfer-v4-0612",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9920943379402161,
"probabilities": [
0.007905662059783936,
0.9920943379402161
],
"target": 1,
"brier": 0.00012499898520701436,
"nll": 0.007937077488805308
},
{
"id": "transfer-v4-0613",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9961675654631108,
"probabilities": [
0.9961675654631108,
0.0038324345368891954
],
"target": 0,
"brier": 2.9375108959082204e-05,
"nll": 0.0038397971312562596
},
{
"id": "transfer-v4-0614",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9947944283485413,
"probabilities": [
0.00520557165145874,
0.9947944283485413
],
"target": 1,
"brier": 5.419595243694175e-05,
"nll": 0.005219167844063148
},
{
"id": "transfer-v4-0615",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9961287009064108,
"probabilities": [
0.9961287009064108,
0.0038712990935891867
],
"target": 0,
"brier": 2.9973913344048917e-05,
"nll": 0.0038788119679158115
},
{
"id": "transfer-v4-0616",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9898474812507629,
"probabilities": [
0.01015251874923706,
0.9898474812507629
],
"target": 1,
"brier": 0.0002061472739072201,
"nll": 0.01020440706452464
},
{
"id": "transfer-v4-0617",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9927447400987148,
"probabilities": [
0.9927447400987148,
0.0072552599012851715
],
"target": 0,
"brier": 0.00010527759247039303,
"nll": 0.007281707298874444
},
{
"id": "transfer-v4-0618",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.995016872882843,
"probabilities": [
0.004983127117156982,
0.995016872882843
],
"target": 1,
"brier": 4.966311173149052e-05,
"nll": 0.00499558429612495
},
{
"id": "transfer-v4-0619",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9958703210577369,
"probabilities": [
0.9958703210577369,
0.004129678942263126
],
"target": 0,
"brier": 3.410849633234299e-05,
"nll": 0.004138229615488951
},
{
"id": "transfer-v4-0620",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9935702085494995,
"probabilities": [
0.006429791450500488,
0.9935702085494995
],
"target": 1,
"brier": 8.268443619385835e-05,
"nll": 0.006450551596333632
},
{
"id": "transfer-v4-0621",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9924325700849295,
"probabilities": [
0.9924325700849295,
0.007567429915070534
],
"target": 0,
"brier": 0.00011453199103900885,
"nll": 0.007596208189809538
},
{
"id": "transfer-v4-0622",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9899818301200867,
"probabilities": [
0.01001816987991333,
0.9899818301200867
],
"target": 1,
"brier": 0.00020072745548560533,
"nll": 0.010068689435981274
},
{
"id": "transfer-v4-0623",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9916168907657266,
"probabilities": [
0.9916168907657266,
0.008383109234273434
],
"target": 0,
"brier": 0.00014055304086752103,
"nll": 0.008418445116108859
},
{
"id": "transfer-v4-0624",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9928431510925293,
"probabilities": [
0.007156848907470703,
0.9928431510925293
],
"target": 1,
"brier": 0.0001024409725687292,
"nll": 0.007182582002702329
},
{
"id": "transfer-v4-0625",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.993994640186429,
"probabilities": [
0.993994640186429,
0.006005359813570976
],
"target": 0,
"brier": 7.212869298090646e-05,
"nll": 0.006023464506671197
},
{
"id": "transfer-v4-0626",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9935511350631714,
"probabilities": [
0.006448864936828613,
0.9935511350631714
],
"target": 1,
"brier": 8.317571794691503e-05,
"nll": 0.006469748699107471
},
{
"id": "transfer-v4-0627",
"question": "decision",
"type": "noul",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9934509638696909,
"probabilities": [
0.9934509638696909,
0.006549036130309105
],
"target": 0,
"brier": 8.577974847218811e-05,
"nll": 0.006570575158847147
},
{
"id": "transfer-v4-0628",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9428854636299435,
"probabilities": [
0.9428854636299435,
0.031584152990749584,
0.02553038337930686
],
"target": 0,
"brier": 0.0049114294604039686,
"nll": 0.05881046329076717,
"ordinalAbsoluteError": 0.0826449197493633
},
{
"id": "transfer-v4-0629",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.8838977362502332,
"probabilities": [
0.0887306183443923,
0.8838977362502332,
0.027371645405374546
],
"target": 1,
"brier": 0.022102065251796192,
"nll": 0.12341390601113442,
"ordinalAbsoluteError": 0.06135897293901771
},
{
"id": "transfer-v4-0630",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.5364190776223219,
"probabilities": [
0.38179041797547286,
0.5364190776223219,
0.08179050440220521
],
"target": 0,
"brier": 0.6766182007544903,
"nll": 0.9628834649790415,
"ordinalAbsoluteError": 0.7000000864267323
},
{
"id": "transfer-v4-0631",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9519910792628491,
"probabilities": [
0.037470752779020865,
0.9519910792628491,
0.010538167958130052
],
"target": 1,
"brier": 0.003819966768086297,
"nll": 0.0491996147568927,
"ordinalAbsoluteError": 0.02693258482089078
},
{
"id": "transfer-v4-0632",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.8186137615247535,
"probabilities": [
0.8186137615247535,
0.09154176643832201,
0.08984447203692442
],
"target": 0,
"brier": 0.04935289166644098,
"nll": 0.2001429040160871,
"ordinalAbsoluteError": 0.27123071051217085
},
{
"id": "transfer-v4-0633",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9218709812265256,
"probabilities": [
0.0608330838692592,
0.9218709812265256,
0.017295934904215295
],
"target": 1,
"brier": 0.0101039570317611,
"nll": 0.08134999881095209,
"ordinalAbsoluteError": 0.043537148965043904
},
{
"id": "transfer-v4-0634",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.4842739710644501,
"probabilities": [
0.3417350744166926,
0.4842739710644501,
0.17399095451885732
],
"target": 0,
"brier": 0.6981068435581121,
"nll": 1.073719478313694,
"ordinalAbsoluteError": 0.8322558801021647
},
{
"id": "transfer-v4-0635",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.7791965727194601,
"probabilities": [
0.007919653444210169,
0.7791965727194601,
0.21288377383632973
],
"target": 2,
"brier": 1.2267619733385675,
"nll": 1.54700892494104,
"ordinalAbsoluteError": 0.7950358796078805
},
{
"id": "transfer-v4-0636",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.5634218412382763,
"probabilities": [
0.4002163082345105,
0.5634218412382763,
0.036361850527213135
],
"target": 0,
"brier": 0.6785068322659326,
"nll": 0.9157501074516007,
"ordinalAbsoluteError": 0.6361455422927026
},
{
"id": "transfer-v4-0637",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.8944140618999519,
"probabilities": [
0.0890484909100623,
0.8944140618999519,
0.016537447189985885
],
"target": 1,
"brier": 0.019351511217388213,
"nll": 0.11158645454484067,
"ordinalAbsoluteError": 0.07251104372007633
},
{
"id": "transfer-v4-0638",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.5779305358796061,
"probabilities": [
0.20305734290438934,
0.5779305358796061,
0.21901212121600455
],
"target": 0,
"brier": 1.0170876122402346,
"nll": 1.594266862468044,
"ordinalAbsoluteError": 1.0159547783116152
},
{
"id": "transfer-v4-0639",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.4952526372102922,
"probabilities": [
0.010579351296352776,
0.4952526372102922,
0.494168011493355
],
"target": 2,
"brier": 0.5012530979341876,
"nll": 0.70487971537899,
"ordinalAbsoluteError": 0.5164113398029979
},
{
"id": "transfer-v4-0640",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9487137344590888,
"probabilities": [
0.9487137344590888,
0.033660366039230255,
0.017625899501680916
],
"target": 0,
"brier": 0.004073973608271176,
"nll": 0.05264817555192408,
"ordinalAbsoluteError": 0.0689121650425921
},
{
"id": "transfer-v4-0641",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.978184540329385,
"probabilities": [
0.010487258639403089,
0.978184540329385,
0.01132820103121197
],
"target": 1,
"brier": 0.0007142250130135182,
"nll": 0.022056935203991476,
"ordinalAbsoluteError": 0.0008409423918089853
},
{
"id": "transfer-v4-0642",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.7403184258228365,
"probabilities": [
0.21012526985397864,
0.7403184258228365,
0.04955630432318491
],
"target": 0,
"brier": 1.1744292882342249,
"nll": 1.5600514029996733,
"ordinalAbsoluteError": 0.8394310344692063
},
{
"id": "transfer-v4-0643",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9626216628439461,
"probabilities": [
0.027261360743474718,
0.9626216628439461,
0.010116976412579123
],
"target": 1,
"brier": 0.0022426750898701846,
"nll": 0.03809481785362888,
"ordinalAbsoluteError": 0.0171443843308956
},
{
"id": "transfer-v4-0644",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.632715981223703,
"probabilities": [
0.632715981223703,
0.3339764376289714,
0.0333075811473256
],
"target": 0,
"brier": 0.2475472063016912,
"nll": 0.45773364437841596,
"ordinalAbsoluteError": 0.4005915999236226
},
{
"id": "transfer-v4-0645",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.831540435178705,
"probabilities": [
0.020161221517367676,
0.831540435178705,
0.14829834330392727
],
"target": 1,
"brier": 0.05077749845954192,
"nll": 0.18447535233283271,
"ordinalAbsoluteError": 0.12813712178655967
},
{
"id": "transfer-v4-0646",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9827036289014955,
"probabilities": [
0.9827036289014955,
0.010042784763619634,
0.0072535863348848735
],
"target": 0,
"brier": 0.00045263649370319955,
"nll": 0.017447700833868648,
"ordinalAbsoluteError": 0.02454995743338938
},
{
"id": "transfer-v4-0647",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9807088005019278,
"probabilities": [
0.013297079314232933,
0.9807088005019278,
0.005994120183839292
],
"target": 1,
"brier": 0.0005848921731417333,
"nll": 0.019479702929899444,
"ordinalAbsoluteError": 0.007302959130393694
},
{
"id": "transfer-v4-0648",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9926426699809131,
"probabilities": [
0.9926426699809131,
0.004331384240398222,
0.003025945778688703
],
"target": 0,
"brier": 8.204754230329122e-05,
"nll": 0.007384528659958379,
"ordinalAbsoluteError": 0.010383275797775628
},
{
"id": "transfer-v4-0649",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9890606034897043,
"probabilities": [
0.0018638725629496365,
0.009075523947346063,
0.9890606034897043
],
"target": 2,
"brier": 0.00020550955185923893,
"nll": 0.010999671694143192,
"ordinalAbsoluteError": 0.01280326907324536
},
{
"id": "transfer-v4-0650",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.926636513595892,
"probabilities": [
0.926636513595892,
0.03318483370101141,
0.04017865270309652
],
"target": 0,
"brier": 0.00809775845816556,
"nll": 0.07619390077998658,
"ordinalAbsoluteError": 0.11354213910720445
},
{
"id": "transfer-v4-0651",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9860285896205472,
"probabilities": [
0.007024471025366984,
0.9860285896205472,
0.006946939354085788
],
"target": 1,
"brier": 0.0002928034675666481,
"nll": 0.014069929241500433,
"ordinalAbsoluteError": 7.753167128121685e-05
},
{
"id": "transfer-v4-0652",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9806475390350506,
"probabilities": [
0.9806475390350506,
0.011838052840759986,
0.0075144081241893665
],
"target": 0,
"brier": 0.0005711235699173973,
"nll": 0.019542171402009423,
"ordinalAbsoluteError": 0.02686686908913872
},
{
"id": "transfer-v4-0653",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9725694774122938,
"probabilities": [
0.00241694881713049,
0.025013573770575653,
0.9725694774122938
],
"target": 2,
"brier": 0.0013839540837953174,
"nll": 0.027813763972202043,
"ordinalAbsoluteError": 0.02984747140483668
},
{
"id": "transfer-v4-0654",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.5589802611330035,
"probabilities": [
0.39003221437191005,
0.5589802611330035,
0.05098752449508647
],
"target": 0,
"brier": 0.6871193594944933,
"nll": 0.9415259423161003,
"ordinalAbsoluteError": 0.6609553101231764
},
{
"id": "transfer-v4-0655",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.6079154314655045,
"probabilities": [
0.013204794097555882,
0.6079154314655045,
0.37887977443693954
],
"target": 2,
"brier": 0.7555258730045564,
"nll": 0.9705363420684207,
"ordinalAbsoluteError": 0.6343250196606163
},
{
"id": "transfer-v4-0656",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.6506525886257227,
"probabilities": [
0.3207270509018135,
0.6506525886257227,
0.028620360472463743
],
"target": 0,
"brier": 0.8855796554954751,
"nll": 1.1371648262867324,
"ordinalAbsoluteError": 0.7078933095706502
},
{
"id": "transfer-v4-0657",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.6323716728813714,
"probabilities": [
0.013469533251638523,
0.35415879386699006,
0.6323716728813714
],
"target": 2,
"brier": 0.26076046649937956,
"nll": 0.45827796769026796,
"ordinalAbsoluteError": 0.38109786037026705
},
{
"id": "transfer-v4-0658",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9751442894517296,
"probabilities": [
0.9751442894517296,
0.013306753201804234,
0.011548957346466136
],
"target": 0,
"brier": 0.0009282544434236219,
"nll": 0.025169829752347397,
"ordinalAbsoluteError": 0.03640466789473651
},
{
"id": "transfer-v4-0659",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.759724824120284,
"probabilities": [
0.21136135650282192,
0.759724824120284,
0.028913819376894065
],
"target": 1,
"brier": 0.10324179211770111,
"nll": 0.2747989847921481,
"ordinalAbsoluteError": 0.18244753712592787
},
{
"id": "transfer-v4-0660",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.6151410043357571,
"probabilities": [
0.6151410043357571,
0.34756342873601404,
0.03729556692822885
],
"target": 0,
"brier": 0.270307742850922,
"nll": 0.48590376211249925,
"ordinalAbsoluteError": 0.42215456259247175
},
{
"id": "transfer-v4-0661",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.9138901727584358,
"probabilities": [
0.027612689573921007,
0.9138901727584358,
0.05849713766764323
],
"target": 2,
"brier": 1.72238534826997,
"nll": 2.8387774546996125,
"ordinalAbsoluteError": 0.9691155519062777
},
{
"id": "transfer-v4-0662",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9946173590170072,
"probabilities": [
0.9946173590170072,
0.0026466386631205517,
0.002736002319872278
],
"target": 0,
"brier": 4.346322885926464e-05,
"nll": 0.00539717958916909,
"ordinalAbsoluteError": 0.008118643302865108
},
{
"id": "transfer-v4-0663",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": true,
"confidence": 0.9567121071297058,
"probabilities": [
0.025874040490734492,
0.9567121071297058,
0.01741385237955977
],
"target": 1,
"brier": 0.0028465498951633366,
"nll": 0.044252761282756736,
"ordinalAbsoluteError": 0.00846018811117466
},
{
"id": "transfer-v4-0664",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.5518245861478026,
"probabilities": [
0.378435086561295,
0.5518245861478026,
0.06974032729090235
],
"target": 0,
"brier": 0.6957170287459007,
"nll": 0.9717107226323164,
"ordinalAbsoluteError": 0.6913052407296073
},
{
"id": "transfer-v4-0665",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.8718299139763428,
"probabilities": [
0.01294042895823078,
0.8718299139763428,
0.11522965706542646
],
"target": 2,
"brier": 1.543073413342183,
"nll": 2.1608281240482374,
"ordinalAbsoluteError": 0.8977107718928043
},
{
"id": "transfer-v4-0666",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.596859161532366,
"probabilities": [
0.36259195478701556,
0.596859161532366,
0.04054888368061843
],
"target": 0,
"brier": 0.7641740867751012,
"nll": 1.0144771684778167,
"ordinalAbsoluteError": 0.6779569288936028
},
{
"id": "transfer-v4-0667",
"question": "decision",
"type": "score",
"source": "legacy_holdout",
"error": null,
"correct": false,
"confidence": 0.5741234932225422,
"probabilities": [
0.05274830679970523,
0.5741234932225422,
0.37312819997775254
],
"target": 2,
"brier": 0.725368423003423,
"nll": 0.9858332187172648,
"ordinalAbsoluteError": 0.6796201068219527
},
{
"id": "transfer-v4-0668",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9879942617121351,
"probabilities": [
0.012005738287864864,
0.9879942617121351
],
"target": 1,
"brier": 0.00028827550367340924,
"nll": 0.012078389234804553
},
{
"id": "transfer-v4-0669",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9782781036074809,
"probabilities": [
0.9782781036074809,
0.02172189639251905
],
"target": 0,
"brier": 0.0009436815657746661,
"nll": 0.02196128985297265
},
{
"id": "transfer-v4-0670",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9879942617121351,
"probabilities": [
0.012005738287864864,
0.9879942617121351
],
"target": 1,
"brier": 0.00028827550367340924,
"nll": 0.012078389234804553
},
{
"id": "transfer-v4-0671",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9882849169552024,
"probabilities": [
0.011715083044797578,
0.9882849169552024
],
"target": 1,
"brier": 0.00027448634149300846,
"nll": 0.011784245322041278
},
{
"id": "transfer-v4-0672",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9911234277278579,
"probabilities": [
0.00887657227214212,
0.9911234277278579
],
"target": 1,
"brier": 0.00015758707060512455,
"nll": 0.008916203741839648
},
{
"id": "transfer-v4-0673",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9867513510613224,
"probabilities": [
0.9867513510613224,
0.013248648938677611
],
"target": 0,
"brier": 0.0003510533974006467,
"nll": 0.013337195236852256
},
{
"id": "transfer-v4-0674",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9911234277278579,
"probabilities": [
0.00887657227214212,
0.9911234277278579
],
"target": 1,
"brier": 0.00015758707060512455,
"nll": 0.008916203741839648
},
{
"id": "transfer-v4-0675",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9912562905744322,
"probabilities": [
0.008743709425567786,
0.9912562905744322
],
"target": 1,
"brier": 0.000152904909037526,
"nll": 0.008782159950383749
},
{
"id": "transfer-v4-0676",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.5729751245394274,
"probabilities": [
0.4270248754605725,
0.5729751245394274
],
"target": 1,
"brier": 0.364700488524235,
"nll": 0.556912975880911
},
{
"id": "transfer-v4-0677",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9804894577166071,
"probabilities": [
0.9804894577166071,
0.019510542283392877
],
"target": 0,
"brier": 0.000761322520384123,
"nll": 0.019703385349885316
},
{
"id": "transfer-v4-0678",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.5729751245394274,
"probabilities": [
0.4270248754605725,
0.5729751245394274
],
"target": 1,
"brier": 0.364700488524235,
"nll": 0.556912975880911
},
{
"id": "transfer-v4-0679",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.5781693630865027,
"probabilities": [
0.42183063691349737,
0.5781693630865027
],
"target": 1,
"brier": 0.35588217247769366,
"nll": 0.5478884375098889
},
{
"id": "transfer-v4-0680",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9876719198100012,
"probabilities": [
0.9876719198100012,
0.012328080189998735
],
"target": 0,
"brier": 0.00030396312234207904,
"nll": 0.012404701349683963
},
{
"id": "transfer-v4-0681",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8010516047321021,
"probabilities": [
0.19894839526789793,
0.8010516047321021
],
"target": 1,
"brier": 0.07916092795934349,
"nll": 0.2218299086056053
},
{
"id": "transfer-v4-0682",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9876719198100012,
"probabilities": [
0.9876719198100012,
0.012328080189998735
],
"target": 0,
"brier": 0.00030396312234207904,
"nll": 0.012404701349683963
},
{
"id": "transfer-v4-0683",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9873105554208216,
"probabilities": [
0.9873105554208216,
0.012689444579178368
],
"target": 0,
"brier": 0.00032204400745607987,
"nll": 0.012770643222834062
},
{
"id": "transfer-v4-0684",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8760828179996576,
"probabilities": [
0.12391718200034241,
0.8760828179996576
],
"target": 1,
"brier": 0.03071093598981197,
"nll": 0.13229465141897379
},
{
"id": "transfer-v4-0685",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9888489858270753,
"probabilities": [
0.9888489858270753,
0.011151014172924783
],
"target": 0,
"brier": 0.0002486902341695379,
"nll": 0.011213652823088083
},
{
"id": "transfer-v4-0686",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8760828179996576,
"probabilities": [
0.12391718200034241,
0.8760828179996576
],
"target": 1,
"brier": 0.03071093598981197,
"nll": 0.13229465141897379
},
{
"id": "transfer-v4-0687",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.869430052199512,
"probabilities": [
0.13056994780048806,
0.869430052199512
],
"target": 1,
"brier": 0.034097022537244344,
"nll": 0.13991739442776419
},
{
"id": "transfer-v4-0688",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.982679675272943,
"probabilities": [
0.982679675272943,
0.017320324727056982
],
"target": 0,
"brier": 0.0005999872973014045,
"nll": 0.017472076362553435
},
{
"id": "transfer-v4-0689",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9755895861035717,
"probabilities": [
0.02441041389642823,
0.9755895861035717
],
"target": 1,
"brier": 0.0011917366131898757,
"nll": 0.02471328704792562
},
{
"id": "transfer-v4-0690",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.982679675272943,
"probabilities": [
0.982679675272943,
0.017320324727056982
],
"target": 0,
"brier": 0.0005999872973014045,
"nll": 0.017472076362553435
},
{
"id": "transfer-v4-0691",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9827056425307921,
"probabilities": [
0.9827056425307921,
0.01729435746920789
],
"target": 0,
"brier": 0.0005981896005454949,
"nll": 0.017445651765182757
},
{
"id": "transfer-v4-0692",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9913432107698955,
"probabilities": [
0.9913432107698955,
0.008656789230104519
],
"target": 0,
"brier": 0.00014987999954890665,
"nll": 0.008694476890380904
},
{
"id": "transfer-v4-0693",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9844251357691292,
"probabilities": [
0.01557486423087083,
0.9844251357691292
],
"target": 1,
"brier": 0.00048515279162011964,
"nll": 0.015697426690119448
},
{
"id": "transfer-v4-0694",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9913432107698955,
"probabilities": [
0.9913432107698955,
0.008656789230104519
],
"target": 0,
"brier": 0.00014987999954890665,
"nll": 0.008694476890380904
},
{
"id": "transfer-v4-0695",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9914987147721225,
"probabilities": [
0.9914987147721225,
0.008501285227877513
],
"target": 0,
"brier": 0.00014454370105145695,
"nll": 0.008537627269094761
},
{
"id": "transfer-v4-0696",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9917849773920809,
"probabilities": [
0.008215022607919049,
0.9917849773920809
],
"target": 1,
"brier": 0.00013497319289724243,
"nll": 0.008248951853593294
},
{
"id": "transfer-v4-0697",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9925073828768247,
"probabilities": [
0.9925073828768247,
0.007492617123175243
],
"target": 0,
"brier": 0.0001122786227089983,
"nll": 0.007520827781632407
},
{
"id": "transfer-v4-0698",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9917849773920809,
"probabilities": [
0.008215022607919049,
0.9917849773920809
],
"target": 1,
"brier": 0.00013497319289724243,
"nll": 0.008248951853593294
},
{
"id": "transfer-v4-0699",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9915575916497938,
"probabilities": [
0.008442408350206113,
0.9915575916497938
],
"target": 1,
"brier": 0.0001425485175032605,
"nll": 0.008478247333691012
},
{
"id": "transfer-v4-0700",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9847257513241674,
"probabilities": [
0.015274248675832554,
0.9847257513241674
],
"target": 1,
"brier": 0.0004666053452223465,
"nll": 0.015392101629105608
},
{
"id": "transfer-v4-0701",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.982495806720014,
"probabilities": [
0.982495806720014,
0.017504193279985935
],
"target": 0,
"brier": 0.0006127935647662112,
"nll": 0.01765920321727994
},
{
"id": "transfer-v4-0702",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9847257513241674,
"probabilities": [
0.015274248675832554,
0.9847257513241674
],
"target": 1,
"brier": 0.0004666053452223465,
"nll": 0.015392101629105608
},
{
"id": "transfer-v4-0703",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9836711114008228,
"probabilities": [
0.016328888599177225,
0.9836711114008228
],
"target": 1,
"brier": 0.0005332652057686807,
"nll": 0.016463674180590016
},
{
"id": "transfer-v4-0704",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9910191126045577,
"probabilities": [
0.9910191126045577,
0.008980887395442297
],
"target": 0,
"brier": 0.0001613126768192294,
"nll": 0.009021458657945769
},
{
"id": "transfer-v4-0705",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9819967516510468,
"probabilities": [
0.01800324834895314,
0.9819967516510468
],
"target": 1,
"brier": 0.0006482339022281691,
"nll": 0.018167278524133256
},
{
"id": "transfer-v4-0706",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9910191126045577,
"probabilities": [
0.9910191126045577,
0.008980887395442297
],
"target": 0,
"brier": 0.0001613126768192294,
"nll": 0.009021458657945769
},
{
"id": "transfer-v4-0707",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9915912899364666,
"probabilities": [
0.9915912899364666,
0.008408710063533406
],
"target": 0,
"brier": 0.00014141280986513561,
"nll": 0.008444262707535203
},
{
"id": "transfer-v4-0708",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9146479759816533,
"probabilities": [
0.08535202401834673,
0.9146479759816533
],
"target": 1,
"brier": 0.014569936008056875,
"nll": 0.0892160134356473
},
{
"id": "transfer-v4-0709",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8280476578488248,
"probabilities": [
0.8280476578488248,
0.17195234215117522
],
"target": 0,
"brier": 0.05913521594254964,
"nll": 0.1886845684648275
},
{
"id": "transfer-v4-0710",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9146479759816533,
"probabilities": [
0.08535202401834673,
0.9146479759816533
],
"target": 1,
"brier": 0.014569936008056875,
"nll": 0.0892160134356473
},
{
"id": "transfer-v4-0711",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9162678805193216,
"probabilities": [
0.0837321194806784,
0.9162678805193216
],
"target": 1,
"brier": 0.014022135665453201,
"nll": 0.08744651108020547
},
{
"id": "transfer-v4-0712",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9832786533071628,
"probabilities": [
0.9832786533071628,
0.01672134669283725
],
"target": 0,
"brier": 0.0005592068704441169,
"nll": 0.016862726668772123
},
{
"id": "transfer-v4-0713",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9659208778978048,
"probabilities": [
0.03407912210219518,
0.9659208778978048
],
"target": 1,
"brier": 0.002322773126512658,
"nll": 0.034673355062265765
},
{
"id": "transfer-v4-0714",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9832786533071628,
"probabilities": [
0.9832786533071628,
0.01672134669283725
],
"target": 0,
"brier": 0.0005592068704441169,
"nll": 0.016862726668772123
},
{
"id": "transfer-v4-0715",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9820011276416502,
"probabilities": [
0.9820011276416502,
0.017998872358349845
],
"target": 0,
"brier": 0.0006479188123443404,
"nll": 0.018162822317077772
},
{
"id": "transfer-v4-0716",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9536027695178366,
"probabilities": [
0.04639723048216334,
0.9536027695178366
],
"target": 1,
"brier": 0.004305405992829978,
"nll": 0.04750807839901429
},
{
"id": "transfer-v4-0717",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.938914863434877,
"probabilities": [
0.0610851365651231,
0.938914863434877
],
"target": 0,
"brier": 1.7631222415578673,
"nll": 2.795486706471363
},
{
"id": "transfer-v4-0718",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9536027695178366,
"probabilities": [
0.04639723048216334,
0.9536027695178366
],
"target": 1,
"brier": 0.004305405992829978,
"nll": 0.04750807839901429
},
{
"id": "transfer-v4-0719",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9471491853731027,
"probabilities": [
0.052850814626897384,
0.9471491853731027
],
"target": 1,
"brier": 0.0055864172134533355,
"nll": 0.054298663490463056
},
{
"id": "transfer-v4-0720",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.6596399152493527,
"probabilities": [
0.3403600847506473,
0.6596399152493527
],
"target": 1,
"brier": 0.23168997458293558,
"nll": 0.4160611758017277
},
{
"id": "transfer-v4-0721",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": false,
"confidence": 0.6422065496444702,
"probabilities": [
0.3577934503555298,
0.6422065496444702
],
"target": 0,
"brier": 0.8248585048125108,
"nll": 1.0277994133977855
},
{
"id": "transfer-v4-0722",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.6596399152493527,
"probabilities": [
0.3403600847506473,
0.6596399152493527
],
"target": 1,
"brier": 0.23168997458293558,
"nll": 0.4160611758017277
},
{
"id": "transfer-v4-0723",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.6539135174129461,
"probabilities": [
0.3460864825870539,
0.6539135174129461
],
"target": 1,
"brier": 0.2395517068589583,
"nll": 0.4247801726405802
},
{
"id": "transfer-v4-0724",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.7271511771425956,
"probabilities": [
0.2728488228574044,
0.7271511771425956
],
"target": 1,
"brier": 0.1488929602693425,
"nll": 0.3186208765154793
},
{
"id": "transfer-v4-0725",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9700562086871953,
"probabilities": [
0.9700562086871953,
0.02994379131280469
],
"target": 0,
"brier": 0.0017932612763695939,
"nll": 0.03040126206337553
},
{
"id": "transfer-v4-0726",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.7271511771425956,
"probabilities": [
0.2728488228574044,
0.7271511771425956
],
"target": 1,
"brier": 0.1488929602693425,
"nll": 0.3186208765154793
},
{
"id": "transfer-v4-0727",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.7312598606568617,
"probabilities": [
0.26874013934313834,
0.7312598606568617
],
"target": 1,
"brier": 0.14444252498833882,
"nll": 0.3129863958680319
},
{
"id": "transfer-v4-0728",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9491134179855129,
"probabilities": [
0.9491134179855129,
0.05088658201448714
],
"target": 0,
"brier": 0.005178888458234253,
"nll": 0.05222697435684346
},
{
"id": "transfer-v4-0729",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9790473762722197,
"probabilities": [
0.020952623727780277,
0.9790473762722197
],
"target": 1,
"brier": 0.0008780248821558824,
"nll": 0.02117524510747119
},
{
"id": "transfer-v4-0730",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9491134179855129,
"probabilities": [
0.9491134179855129,
0.05088658201448714
],
"target": 0,
"brier": 0.005178888458234253,
"nll": 0.05222697435684346
},
{
"id": "transfer-v4-0731",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9482262836570995,
"probabilities": [
0.9482262836570995,
0.051773716342900504
],
"target": 0,
"brier": 0.005361035407910246,
"nll": 0.053162109369612735
},
{
"id": "transfer-v4-0732",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9558271000904038,
"probabilities": [
0.04417289990959614,
0.9558271000904038
],
"target": 1,
"brier": 0.0039024901728463997,
"nll": 0.045178239933473106
},
{
"id": "transfer-v4-0733",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9551131262761703,
"probabilities": [
0.9551131262761703,
0.04488687372382969
],
"target": 0,
"brier": 0.004029662865398066,
"nll": 0.04592548868317735
},
{
"id": "transfer-v4-0734",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9558271000904038,
"probabilities": [
0.04417289990959614,
0.9558271000904038
],
"target": 1,
"brier": 0.0039024901728463997,
"nll": 0.045178239933473106
},
{
"id": "transfer-v4-0735",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9250178085646708,
"probabilities": [
0.07498219143532929,
0.9250178085646708
],
"target": 1,
"brier": 0.011244658064888731,
"nll": 0.07794228915269215
},
{
"id": "transfer-v4-0736",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9691116466514078,
"probabilities": [
0.030888353348592197,
0.9691116466514078
],
"target": 1,
"brier": 0.0019081807451749731,
"nll": 0.031375455305997973
},
{
"id": "transfer-v4-0737",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9885441430717673,
"probabilities": [
0.9885441430717673,
0.011455856928232663
],
"target": 0,
"brier": 0.00026247331592027344,
"nll": 0.011521980745611745
},
{
"id": "transfer-v4-0738",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9691116466514078,
"probabilities": [
0.030888353348592197,
0.9691116466514078
],
"target": 1,
"brier": 0.0019081807451749731,
"nll": 0.031375455305997973
},
{
"id": "transfer-v4-0739",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9684248439577332,
"probabilities": [
0.031575156042266746,
0.9684248439577332
],
"target": 1,
"brier": 0.0019939809581869914,
"nll": 0.032084399602809004
},
{
"id": "transfer-v4-0740",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9760714878447893,
"probabilities": [
0.023928512155210736,
0.9760714878447893
],
"target": 1,
"brier": 0.0011451473879241364,
"nll": 0.02421944950877105
},
{
"id": "transfer-v4-0741",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.7153855562210083,
"probabilities": [
0.7153855562210083,
0.2846144437789917
],
"target": 0,
"brier": 0.16201076321524965,
"nll": 0.3349336421555453
},
{
"id": "transfer-v4-0742",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9760714878447893,
"probabilities": [
0.023928512155210736,
0.9760714878447893
],
"target": 1,
"brier": 0.0011451473879241364,
"nll": 0.02421944950877105
},
{
"id": "transfer-v4-0743",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9696273821771655,
"probabilities": [
0.03037261782283451,
0.9696273821771655
],
"target": 1,
"brier": 0.0018449918268239292,
"nll": 0.03084342337157661
},
{
"id": "transfer-v4-0744",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8549255132675171,
"probabilities": [
0.8549255132675171,
0.1450744867324829
],
"target": 0,
"brier": 0.04209321340138672,
"nll": 0.1567409328258162
},
{
"id": "transfer-v4-0745",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8562704537986016,
"probabilities": [
0.14372954620139838,
0.8562704537986016
],
"target": 1,
"brier": 0.041316364902519845,
"nll": 0.15516900204300552
},
{
"id": "transfer-v4-0746",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8549255132675171,
"probabilities": [
0.8549255132675171,
0.1450744867324829
],
"target": 0,
"brier": 0.04209321340138672,
"nll": 0.1567409328258162
},
{
"id": "transfer-v4-0747",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9011222258377407,
"probabilities": [
0.9011222258377407,
0.09887777416225932
],
"target": 0,
"brier": 0.01955362844656551,
"nll": 0.10411437481645056
},
{
"id": "transfer-v4-0748",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.6996611952781677,
"probabilities": [
0.6996611952781677,
0.3003388047218323
],
"target": 0,
"brier": 0.1804067952434778,
"nll": 0.3571590678532805
},
{
"id": "transfer-v4-0749",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.568324940452723,
"probabilities": [
0.4316750595472771,
0.568324940452723
],
"target": 1,
"brier": 0.3726867140702904,
"nll": 0.5650619455735364
},
{
"id": "transfer-v4-0750",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.6996611952781677,
"probabilities": [
0.6996611952781677,
0.3003388047218323
],
"target": 0,
"brier": 0.1804067952434778,
"nll": 0.3571590678532805
},
{
"id": "transfer-v4-0751",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.7064234824902857,
"probabilities": [
0.7064234824902857,
0.2935765175097143
],
"target": 0,
"brier": 0.17237434326626316,
"nll": 0.34754038776148893
},
{
"id": "transfer-v4-0752",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8233854542695934,
"probabilities": [
0.8233854542695934,
0.1766145457304066
],
"target": 0,
"brier": 0.062385395527115764,
"nll": 0.19433083525100425
},
{
"id": "transfer-v4-0753",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.6428949236869812,
"probabilities": [
0.3571050763130188,
0.6428949236869812
],
"target": 1,
"brier": 0.25504807105705396,
"nll": 0.44177398382619004
},
{
"id": "transfer-v4-0754",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8233854542695934,
"probabilities": [
0.8233854542695934,
0.1766145457304066
],
"target": 0,
"brier": 0.062385395527115764,
"nll": 0.19433083525100425
},
{
"id": "transfer-v4-0755",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8616960773124707,
"probabilities": [
0.8616960773124707,
0.13830392268752936
],
"target": 0,
"brier": 0.03825595006151619,
"nll": 0.14885264901268136
},
{
"id": "transfer-v4-0756",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8845843343219036,
"probabilities": [
0.11541566567809636,
0.8845843343219036
],
"target": 1,
"brier": 0.026641551767836218,
"nll": 0.12263742304012451
},
{
"id": "transfer-v4-0757",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9147244095802307,
"probabilities": [
0.9147244095802307,
0.08527559041976929
],
"target": 0,
"brier": 0.014543852642880495,
"nll": 0.0891324507895451
},
{
"id": "transfer-v4-0758",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8845843343219036,
"probabilities": [
0.11541566567809636,
0.8845843343219036
],
"target": 1,
"brier": 0.026641551767836218,
"nll": 0.12263742304012451
},
{
"id": "transfer-v4-0759",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8842220770683575,
"probabilities": [
0.11577792293164249,
0.8842220770683575
],
"target": 1,
"brier": 0.02680905487673069,
"nll": 0.12304702949143341
},
{
"id": "transfer-v4-0760",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8787374758344136,
"probabilities": [
0.8787374758344136,
0.12126252416558636
],
"target": 0,
"brier": 0.029409199534018833,
"nll": 0.12926908820984956
},
{
"id": "transfer-v4-0761",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9860226577088529,
"probabilities": [
0.013977342291147117,
0.9860226577088529
],
"target": 1,
"brier": 0.00039073219504777933,
"nll": 0.014075945222781184
},
{
"id": "transfer-v4-0762",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.8787374758344136,
"probabilities": [
0.8787374758344136,
0.12126252416558636
],
"target": 0,
"brier": 0.029409199534018833,
"nll": 0.12926908820984956
},
{
"id": "transfer-v4-0763",
"question": "decision",
"type": "choice",
"source": "composition_holdout",
"error": null,
"correct": true,
"confidence": 0.9202984502889331,
"probabilities": [
0.9202984502889331,
0.07970154971106685
],
"target": 0,
"brier": 0.012704674052691331,
"nll": 0.08305725905819046
},
{
"id": "ru-public-0-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7779900911749886,
"probabilities": [
0.7779900911749886,
0.09111599488383539,
0.13089391394117603
],
"target": 0,
"brier": 0.07472374084700098,
"nll": 0.2510414911637875
},
{
"id": "ru-public-0-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8656439781188965,
"probabilities": [
0.8656439781188965,
0.13435602188110352
],
"target": 0,
"brier": 0.03610308123143113,
"nll": 0.14428156566609043
},
{
"id": "ru-public-0-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.776918697701116,
"probabilities": [
0.776918697701116,
0.13197503787316325,
0.0911062644257208
],
"target": 0,
"brier": 0.07548302947459831,
"nll": 0.25241957025253475,
"ordinalAbsoluteError": 0.31418756672460485
},
{
"id": "ru-public-0-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.6921958923339844,
"probabilities": [
0.129063680768013,
0.6921958923339844,
0.17874042689800262
],
"target": 1,
"brier": 0.14334894259713993,
"nll": 0.3678862820169573
},
{
"id": "ru-public-0-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9745318796485662,
"probabilities": [
0.9745318796485662,
0.025468120351433754
],
"target": 0,
"brier": 0.0012972503084702283,
"nll": 0.02579804671782112
},
{
"id": "ru-public-0-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8955196075475245,
"probabilities": [
0.8955196075475245,
0.060756455654230296,
0.04372393679824518
],
"target": 0,
"brier": 0.0165192819598247,
"nll": 0.11035116207894995,
"ordinalAbsoluteError": 0.14820432925072066
},
{
"id": "ru-public-0-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7791858837952685,
"probabilities": [
0.10517799069435832,
0.11563612551037318,
0.7791858837952685
],
"target": 2,
"brier": 0.07319299716482995,
"nll": 0.24950564309708628
},
{
"id": "ru-public-0-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9612753503024578,
"probabilities": [
0.9612753503024578,
0.03872464969754219
],
"target": 0,
"brier": 0.002999196988394709,
"nll": 0.03949438628380038
},
{
"id": "ru-public-0-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.5546622707050362,
"probabilities": [
0.34724660673002583,
0.5546622707050362,
0.09809112256493799
],
"target": 1,
"brier": 0.3285277673451614,
"nll": 0.5893958717120925,
"ordinalAbsoluteError": 0.24915548416508781
},
{
"id": "ru-public-0-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8131175576663199,
"probabilities": [
0.8131175576663199,
0.06529169481030334,
0.12159074752337673
],
"target": 0,
"brier": 0.053972362547096614,
"nll": 0.2068795825119721
},
{
"id": "ru-public-0-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7270898222923279,
"probabilities": [
0.2729101777076721,
0.7270898222923279
],
"target": 1,
"brier": 0.14895993019286635,
"nll": 0.31870525709659064
},
{
"id": "ru-public-0-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7729507992807478,
"probabilities": [
0.16101127263116566,
0.7729507992807478,
0.06603792808808655
],
"target": 1,
"brier": 0.08183697740772611,
"nll": 0.2575398814750621,
"ordinalAbsoluteError": 0.09497334454307904
},
{
"id": "ru-public-0-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7139491598445734,
"probabilities": [
0.11004973448924127,
0.7139491598445734,
0.1760011056661853
],
"target": 1,
"brier": 0.12491241641049763,
"nll": 0.33694352387720466
},
{
"id": "ru-public-0-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.719184935092926,
"probabilities": [
0.280815064907074,
0.719184935092926
],
"target": 1,
"brier": 0.15771420135752834,
"nll": 0.32963674280033367
},
{
"id": "ru-public-0-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8834218580295561,
"probabilities": [
0.08629355027437695,
0.8834218580295561,
0.030284591696066968
],
"target": 1,
"brier": 0.021954196498434886,
"nll": 0.12395243705409725,
"ordinalAbsoluteError": 0.05600895857831001
},
{
"id": "ru-public-0-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7843251952931168,
"probabilities": [
0.09951516392736649,
0.11615964077951665,
0.7843251952931168
],
"target": 2,
"brier": 0.06991195138286917,
"nll": 0.24293155471859512
},
{
"id": "ru-public-0-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7603375315666199,
"probabilities": [
0.23966246843338013,
0.7603375315666199
],
"target": 1,
"brier": 0.11487619755116185,
"nll": 0.273992823811677
},
{
"id": "ru-public-0-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": false,
"confidence": 0.3918795883655548,
"probabilities": [
0.3918795883655548,
0.25547391176223755,
0.35264649987220764
],
"target": 2,
"brier": 0.6379030854963599,
"nll": 1.0422891405942531,
"ordinalAbsoluteError": 1.0392330884933472
},
{
"id": "ru-public-0-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8127528065702555,
"probabilities": [
0.8127528065702555,
0.06790711427150156,
0.11934007915824298
],
"target": 0,
"brier": 0.05391494210949462,
"nll": 0.2073282666262863
},
{
"id": "ru-public-0-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7266669869422913,
"probabilities": [
0.27333301305770874,
0.7266669869422913
],
"target": 1,
"brier": 0.14942187205441115,
"nll": 0.3192869711209368
},
{
"id": "ru-public-0-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7556228435736888,
"probabilities": [
0.14508398633888292,
0.09929317008742831,
0.7556228435736888
],
"target": 2,
"brier": 0.0906286913010019,
"nll": 0.28021291144849864,
"ordinalAbsoluteError": 0.38946114276519417
},
{
"id": "ru-public-0-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7036057219446558,
"probabilities": [
0.11765925761549559,
0.7036057219446558,
0.1787350204398486
],
"target": 1,
"brier": 0.13363947649821137,
"nll": 0.35153713376883433
},
{
"id": "ru-public-0-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8782506287097931,
"probabilities": [
0.8782506287097931,
0.12174937129020691
],
"target": 0,
"brier": 0.029645818819121317,
"nll": 0.12982327196991195
},
{
"id": "ru-public-0-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7648041248321533,
"probabilities": [
0.7648041248321533,
0.14319072663784027,
0.09200514853000641
],
"target": 0,
"brier": 0.08428563124707056,
"nll": 0.2681355239120088,
"ordinalAbsoluteError": 0.3272010236978531
},
{
"id": "ru-public-1-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7372539960870893,
"probabilities": [
0.7372539960870893,
0.08702376905740168,
0.175722234855509
],
"target": 0,
"brier": 0.10748690277577393,
"nll": 0.3048228110408926
},
{
"id": "ru-public-1-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.973212007433176,
"probabilities": [
0.973212007433176,
0.02678799256682396
],
"target": 0,
"brier": 0.0014351930915204314,
"nll": 0.027153330054785298
},
{
"id": "ru-public-1-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8713336392193964,
"probabilities": [
0.8713336392193964,
0.07203519928376677,
0.05663116149683681
],
"target": 0,
"brier": 0.024951190784857243,
"nll": 0.13773032241098068,
"ordinalAbsoluteError": 0.1852975222774404
},
{
"id": "ru-public-1-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7869663942128177,
"probabilities": [
0.0781365106823901,
0.7869663942128177,
0.13489709510479228
],
"target": 1,
"brier": 0.06968585776401924,
"nll": 0.2395697326037494
},
{
"id": "ru-public-1-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9762326180934906,
"probabilities": [
0.9762326180934906,
0.0237673819065094
],
"target": 0,
"brier": 0.0011297768853797407,
"nll": 0.024054382756540083
},
{
"id": "ru-public-1-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.48615921268104334,
"probabilities": [
0.4113826813009781,
0.48615921268104334,
0.10245810601797858
],
"target": 1,
"brier": 0.4437657286757387,
"nll": 0.7212191106210447,
"ordinalAbsoluteError": 0.30892457528299944
},
{
"id": "ru-public-1-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7925127331347083,
"probabilities": [
0.11273819365227702,
0.09474907321301466,
0.7925127331347083
],
"target": 2,
"brier": 0.06473825309393232,
"nll": 0.23254670631282448
},
{
"id": "ru-public-1-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7471219301223755,
"probabilities": [
0.2528780698776245,
0.7471219301223755
],
"target": 1,
"brier": 0.1278946364500655,
"nll": 0.2915268807671904
},
{
"id": "ru-public-1-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7162176593130558,
"probabilities": [
0.19556992226101863,
0.7162176593130558,
0.0882124184259256
],
"target": 1,
"brier": 0.12656144214349233,
"nll": 0.3337711647641508,
"ordinalAbsoluteError": 0.10735750383509302
},
{
"id": "ru-public-1-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7585302904795747,
"probabilities": [
0.7585302904795747,
0.0844870997783877,
0.1569826097420376
],
"target": 0,
"brier": 0.09008923040626271,
"nll": 0.27637254627823044
},
{
"id": "ru-public-1-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.6417388916015625,
"probabilities": [
0.3582611083984375,
0.6417388916015625
],
"target": 1,
"brier": 0.25670204358175397,
"nll": 0.4435737689224794
},
{
"id": "ru-public-1-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8302307561905331,
"probabilities": [
0.12398478290359288,
0.8302307561905331,
0.04578446090587397
],
"target": 1,
"brier": 0.04629003939573077,
"nll": 0.18605159732508844,
"ordinalAbsoluteError": 0.07820032199771898
},
{
"id": "ru-public-1-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7915812134742737,
"probabilities": [
0.0795540064573288,
0.7915812134742737,
0.12886478006839752
],
"target": 1,
"brier": 0.06637336206234545,
"nll": 0.23372279788214229
},
{
"id": "ru-public-1-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7217962741851807,
"probabilities": [
0.27820372581481934,
0.7217962741851807
],
"target": 1,
"brier": 0.15479462611449435,
"nll": 0.3260123486249803
},
{
"id": "ru-public-1-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.4601461383635042,
"probabilities": [
0.3023624881045898,
0.237491373531906,
0.4601461383635042
],
"target": 2,
"brier": 0.43926741863870633,
"nll": 0.7762111478578699,
"ordinalAbsoluteError": 0.8422163497410855
},
{
"id": "ru-public-1-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8018044770973942,
"probabilities": [
0.10788534560030781,
0.09031017730229791,
0.8018044770973942
],
"target": 2,
"brier": 0.05907664121830768,
"nll": 0.2208904949811455
},
{
"id": "ru-public-1-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7265133261680603,
"probabilities": [
0.2734866738319397,
0.7265133261680603
],
"target": 1,
"brier": 0.14958992152731554,
"nll": 0.3194984531695406
},
{
"id": "ru-public-1-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.6437337398529053,
"probabilities": [
0.19219887256622314,
0.16406738758087158,
0.6437337398529053
],
"target": 2,
"brier": 0.1907841624025366,
"nll": 0.4404700858041158,
"ordinalAbsoluteError": 0.5484651327133179
},
{
"id": "ru-public-1-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7283811570122296,
"probabilities": [
0.7283811570122296,
0.1078377975986583,
0.1637810453891121
],
"target": 0,
"brier": 0.11223001728569466,
"nll": 0.3169308004745097
},
{
"id": "ru-public-1-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.85249824821949,
"probabilities": [
0.85249824821949,
0.14750175178050995
],
"target": 0,
"brier": 0.04351353355663834,
"nll": 0.15958412470107491
},
{
"id": "ru-public-1-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7430390119552612,
"probabilities": [
0.7430390119552612,
0.15730254352092743,
0.09965844452381134
],
"target": 0,
"brier": 0.10070484513998723,
"nll": 0.2970067296464556,
"ordinalAbsoluteError": 0.3566194325685501
},
{
"id": "ru-public-1-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7750839302285042,
"probabilities": [
0.08672176723473642,
0.7750839302285042,
0.13819430253675943
],
"target": 1,
"brier": 0.07720556860739357,
"nll": 0.25478395842345664
},
{
"id": "ru-public-1-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.975872615352273,
"probabilities": [
0.975872615352273,
0.024127384647727013
],
"target": 0,
"brier": 0.0011642613798787463,
"nll": 0.02442321814423419
},
{
"id": "ru-public-1-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8604624527830617,
"probabilities": [
0.8604624527830617,
0.08446391923618075,
0.05507362798075759
],
"target": 0,
"brier": 0.029637985235018247,
"nll": 0.1502852984684085,
"ordinalAbsoluteError": 0.19461117519769594
},
{
"id": "ru-public-2-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.84839855676444,
"probabilities": [
0.84839855676444,
0.049306999340947726,
0.1022944438946123
],
"target": 0,
"brier": 0.03587833102682093,
"nll": 0.16440475741936494
},
{
"id": "ru-public-2-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9890693239867687,
"probabilities": [
0.9890693239867687,
0.010930676013231277
],
"target": 0,
"brier": 0.00023895935621245923,
"nll": 0.010990854783844843
},
{
"id": "ru-public-2-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.5230681779294868,
"probabilities": [
0.3573011676080264,
0.5230681779294868,
0.11963065446248677
],
"target": 1,
"brier": 0.36943958076468153,
"nll": 0.6480434640834506,
"ordinalAbsoluteError": 0.23767051314553966
},
{
"id": "ru-public-2-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.828805519520928,
"probabilities": [
0.062063165266262446,
0.828805519520928,
0.10913131521280957
],
"target": 1,
"brier": 0.045069030589444385,
"nll": 0.18776974784546455
},
{
"id": "ru-public-2-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7176650166511536,
"probabilities": [
0.28233498334884644,
0.7176650166511536
],
"target": 1,
"brier": 0.1594260856451868,
"nll": 0.33175236942765324
},
{
"id": "ru-public-2-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7605011123194794,
"probabilities": [
0.1404687401442793,
0.7605011123194794,
0.09903014753624137
],
"target": 1,
"brier": 0.08689815427897743,
"nll": 0.2737777046678442,
"ordinalAbsoluteError": 0.04143859260803784
},
{
"id": "ru-public-2-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7716867521270568,
"probabilities": [
0.14059966069312674,
0.08771358717981644,
0.7716867521270568
],
"target": 2,
"brier": 0.07958887711726562,
"nll": 0.25917657279428064
},
{
"id": "ru-public-2-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8108749985694885,
"probabilities": [
0.18912500143051147,
0.8108749985694885
],
"target": 1,
"brier": 0.07153653233218193,
"nll": 0.2096413692130754
},
{
"id": "ru-public-2-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8644255866940977,
"probabilities": [
0.07830443861626925,
0.8644255866940977,
0.05726997468963303
],
"target": 1,
"brier": 0.027791856651199893,
"nll": 0.14569005426216017,
"ordinalAbsoluteError": 0.021034463926636215
},
{
"id": "ru-public-2-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.855523694971497,
"probabilities": [
0.855523694971497,
0.048504631716378414,
0.09597167331212456
],
"target": 0,
"brier": 0.03243666409095969,
"nll": 0.1560414888136987
},
{
"id": "ru-public-2-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7189074158668518,
"probabilities": [
0.2810925841331482,
0.7189074158668518
],
"target": 1,
"brier": 0.158026081709302,
"nll": 0.3300226974705382
},
{
"id": "ru-public-2-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.5578731464705808,
"probabilities": [
0.2250264801092887,
0.21710037342013042,
0.5578731464705808
],
"target": 2,
"brier": 0.2932456435013606,
"nll": 0.5836236785198163,
"ordinalAbsoluteError": 0.6671533336387079
},
{
"id": "ru-public-2-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8379013192028201,
"probabilities": [
0.0609977412521166,
0.8379013192028201,
0.10110093954506336
],
"target": 1,
"brier": 0.04021810673094075,
"nll": 0.176854942948549
},
{
"id": "ru-public-2-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7766926288604736,
"probabilities": [
0.22330737113952637,
0.7766926288604736
],
"target": 1,
"brier": 0.09973236401049235,
"nll": 0.25271059393184614
},
{
"id": "ru-public-2-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.796261495045397,
"probabilities": [
0.10592525575442473,
0.09781324920017824,
0.796261495045397
],
"target": 2,
"brier": 0.062296969926873245,
"nll": 0.22782763572223325,
"ordinalAbsoluteError": 0.3096637607090278
},
{
"id": "ru-public-2-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7184937871175802,
"probabilities": [
0.1485679083212655,
0.13293830456115435,
0.7184937871175802
],
"target": 2,
"brier": 0.11899076409395247,
"nll": 0.3305982205184248
},
{
"id": "ru-public-2-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8950637429952621,
"probabilities": [
0.8950637429952621,
0.10493625700473785
],
"target": 0,
"brier": 0.02202323606832879,
"nll": 0.11086034201963603
},
{
"id": "ru-public-2-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7264235615730286,
"probabilities": [
0.7264235615730286,
0.16165149211883545,
0.11192494630813599
],
"target": 0,
"brier": 0.11350246617271154,
"nll": 0.31962201613487423,
"ordinalAbsoluteError": 0.3855013847351074
},
{
"id": "ru-public-2-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8565071853120148,
"probabilities": [
0.8565071853120148,
0.04844000581070783,
0.0950528088772774
],
"target": 0,
"brier": 0.031971658505482115,
"nll": 0.1548925720972671
},
{
"id": "ru-public-2-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9894221629947424,
"probabilities": [
0.9894221629947424,
0.010577837005257607
],
"target": 0,
"brier": 0.00022378127141959442,
"nll": 0.010634180000014894
},
{
"id": "ru-public-2-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9051961797640155,
"probabilities": [
0.9051961797640155,
0.05057965907551729,
0.044224161160467255
],
"target": 0,
"brier": 0.013501842673879412,
"nll": 0.0996035855542239,
"ordinalAbsoluteError": 0.1390279813964518
},
{
"id": "ru-public-2-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8258391845596201,
"probabilities": [
0.06435580263931441,
0.8258391845596201,
0.10980501280106547
],
"target": 1,
"brier": 0.0465307998044506,
"nll": 0.19135521623251148
},
{
"id": "ru-public-2-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9822903871536255,
"probabilities": [
0.9822903871536255,
0.01770961284637451
],
"target": 0,
"brier": 0.0006272607743369463,
"nll": 0.0178683044088269
},
{
"id": "ru-public-2-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.47912004590034485,
"probabilities": [
0.4027947783470154,
0.47912004590034485,
0.11808517575263977
],
"target": 1,
"brier": 0.44750366877901193,
"nll": 0.7358040952245805,
"ordinalAbsoluteError": 0.2847096025943756
},
{
"id": "ru-public-3-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8009707509965058,
"probabilities": [
0.8009707509965058,
0.06828624399003604,
0.13074300501345817
],
"target": 0,
"brier": 0.06136938643711077,
"nll": 0.22193084819034434
},
{
"id": "ru-public-3-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7570141553878784,
"probabilities": [
0.24298584461212158,
0.7570141553878784
],
"target": 1,
"brier": 0.11808424136373219,
"nll": 0.27837332639603307
},
{
"id": "ru-public-3-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.782961040100494,
"probabilities": [
0.14616999574638886,
0.782961040100494,
0.0708689641531171
],
"target": 1,
"brier": 0.07349398785089449,
"nll": 0.2446723414444708,
"ordinalAbsoluteError": 0.07530103159327173
},
{
"id": "ru-public-3-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7990561187196978,
"probabilities": [
0.07232461178544619,
0.7990561187196978,
0.12861926949485591
],
"target": 1,
"brier": 0.062152209379298044,
"nll": 0.22432409948744256
},
{
"id": "ru-public-3-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7493141889572144,
"probabilities": [
0.25068581104278564,
0.7493141889572144
],
"target": 1,
"brier": 0.12568675171635846,
"nll": 0.2885969055076774
},
{
"id": "ru-public-3-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8875658612195853,
"probabilities": [
0.0773717792310689,
0.8875658612195853,
0.03506235954934585
],
"target": 1,
"brier": 0.019857196841842433,
"nll": 0.11927255056109423,
"ordinalAbsoluteError": 0.04230941968172308
},
{
"id": "ru-public-3-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8029217482919282,
"probabilities": [
0.09716886716345849,
0.09990938454461326,
0.8029217482919282
],
"target": 2,
"brier": 0.058263511162223364,
"nll": 0.21949801898444476
},
{
"id": "ru-public-3-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7856099605560303,
"probabilities": [
0.21439003944396973,
0.7856099605560303
],
"target": 1,
"brier": 0.09192617802557379,
"nll": 0.24129484310674054
},
{
"id": "ru-public-3-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.3972605287212291,
"probabilities": [
0.3289449014945299,
0.273794569784241,
0.3972605287212291
],
"target": 2,
"brier": 0.5464630848999958,
"nll": 0.9231629698983391,
"ordinalAbsoluteError": 0.9316843727733009
},
{
"id": "ru-public-3-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7991071701315888,
"probabilities": [
0.7991071701315888,
0.07016052096603748,
0.13073230890237364
],
"target": 0,
"brier": 0.06237136438570982,
"nll": 0.22426021188313516
},
{
"id": "ru-public-3-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7704685926437378,
"probabilities": [
0.2295314073562622,
0.7704685926437378
],
"target": 1,
"brier": 0.10536933392589276,
"nll": 0.260756387358109
},
{
"id": "ru-public-3-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8070595740220015,
"probabilities": [
0.10876398371511722,
0.08417644226288136,
0.8070595740220015
],
"target": 2,
"brier": 0.05614128556219002,
"nll": 0.2143577918482661,
"ordinalAbsoluteError": 0.3017044096931156
},
{
"id": "ru-public-3-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7683742275349565,
"probabilities": [
0.09115636620391507,
0.7683742275349565,
0.14046940626112836
],
"target": 1,
"brier": 0.08169163566488429,
"nll": 0.2634783890784472
},
{
"id": "ru-public-3-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8742038607597351,
"probabilities": [
0.8742038607597351,
0.1257961392402649
],
"target": 0,
"brier": 0.031649337295512225,
"nll": 0.1344416802280431
},
{
"id": "ru-public-3-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7495004534721375,
"probabilities": [
0.7495004534721375,
0.15390700101852417,
0.09659254550933838
],
"target": 0,
"brier": 0.09576750762115438,
"nll": 0.28834835640679585,
"ordinalAbsoluteError": 0.3470920920372009
},
{
"id": "ru-public-3-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8110799314242592,
"probabilities": [
0.0895347906579791,
0.09938527791776178,
0.8110799314242592
],
"target": 2,
"brier": 0.05358470451562151,
"nll": 0.20938867063055444
},
{
"id": "ru-public-3-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9762317463755608,
"probabilities": [
0.9762317463755608,
0.02376825362443924
],
"target": 0,
"brier": 0.001129859760711338,
"nll": 0.024055275697733483
},
{
"id": "ru-public-3-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8803075852887025,
"probabilities": [
0.8803075852887025,
0.06994729254571486,
0.0497451221655827
],
"target": 0,
"brier": 0.021693475053165802,
"nll": 0.1274839038436618,
"ordinalAbsoluteError": 0.16943753687688026
},
{
"id": "ru-public-3-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8041009603403151,
"probabilities": [
0.8041009603403151,
0.06718914705555339,
0.12870989260413152
],
"target": 0,
"brier": 0.05945705167580665,
"nll": 0.218030445124164
},
{
"id": "ru-public-3-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9772861339151859,
"probabilities": [
0.9772861339151859,
0.02271386608481407
],
"target": 0,
"brier": 0.0010318394250377338,
"nll": 0.022975799893954055
},
{
"id": "ru-public-3-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.5115107336007858,
"probabilities": [
0.391422185237871,
0.5115107336007858,
0.09706708116134316
],
"target": 1,
"brier": 0.4012551087288154,
"nll": 0.6703867092538626,
"ordinalAbsoluteError": 0.2943551040765279
},
{
"id": "ru-public-3-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7938826739332279,
"probabilities": [
0.07175431453998621,
0.7938826739332279,
0.13436301152678587
],
"target": 1,
"brier": 0.06568645262656653,
"nll": 0.2308195944806157
},
{
"id": "ru-public-3-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.780590295791626,
"probabilities": [
0.21940970420837402,
0.780590295791626
],
"target": 1,
"brier": 0.09628123660161236,
"nll": 0.24770485604281509
},
{
"id": "ru-public-3-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7940582928828259,
"probabilities": [
0.13951716346730156,
0.7940582928828259,
0.06642454364987253
],
"target": 1,
"brier": 0.06628924563139148,
"nll": 0.23059840370087759,
"ordinalAbsoluteError": 0.07309261981742898
},
{
"id": "ru-public-4-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8529616840832736,
"probabilities": [
0.8529616840832736,
0.0398309102723747,
0.10720740564435176
],
"target": 0,
"brier": 0.0347001955857456,
"nll": 0.1590406515107496
},
{
"id": "ru-public-4-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.6715852618217468,
"probabilities": [
0.3284147381782532,
0.6715852618217468
],
"target": 1,
"brier": 0.21571248050538117,
"nll": 0.3981142988948461
},
{
"id": "ru-public-4-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.82123733632342,
"probabilities": [
0.11392337149838379,
0.82123733632342,
0.06483929217819619
],
"target": 1,
"brier": 0.04913875830847431,
"nll": 0.19694312930413013,
"ordinalAbsoluteError": 0.04908407932018766
},
{
"id": "ru-public-4-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8158419253802587,
"probabilities": [
0.06897783382203927,
0.8158419253802587,
0.11518024079770209
],
"target": 1,
"brier": 0.051938625876647715,
"nll": 0.20353466168070092
},
{
"id": "ru-public-4-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7408612966537476,
"probabilities": [
0.25913870334625244,
0.7408612966537476
],
"target": 1,
"brier": 0.13430573514395405,
"nll": 0.2999418552102019
},
{
"id": "ru-public-4-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.5675123845411482,
"probabilities": [
0.22880397396081725,
0.20368364149803458,
0.5675123845411482
],
"target": 2,
"brier": 0.2808838218394459,
"nll": 0.5664927068847003,
"ordinalAbsoluteError": 0.6612915894196691
},
{
"id": "ru-public-4-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7480681371375589,
"probabilities": [
0.15540650139585507,
0.09652536146658595,
0.7480681371375589
],
"target": 2,
"brier": 0.09693798960769479,
"nll": 0.2902612127264316
},
{
"id": "ru-public-4-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8430377840995789,
"probabilities": [
0.15696221590042114,
0.8430377840995789
],
"target": 1,
"brier": 0.04927427444074084,
"nll": 0.17074350098877072
},
{
"id": "ru-public-4-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8229995431229438,
"probabilities": [
0.08542286668287863,
0.09157759019417755,
0.8229995431229438
],
"target": 2,
"brier": 0.047012682912780226,
"nll": 0.19479963344137713,
"ordinalAbsoluteError": 0.2624233235599349
},
{
"id": "ru-public-4-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7735569419446815,
"probabilities": [
0.7735569419446815,
0.06904111006080277,
0.15740194799451568
],
"target": 0,
"brier": 0.08081850665234044,
"nll": 0.25675599571902735
},
{
"id": "ru-public-4-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9148422107100487,
"probabilities": [
0.9148422107100487,
0.08515778928995132
],
"target": 0,
"brier": 0.014503698153503497,
"nll": 0.0890036758887852
},
{
"id": "ru-public-4-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7882267715301101,
"probabilities": [
0.7882267715301101,
0.12667138685775717,
0.08510184161213276
],
"target": 0,
"brier": 0.06813586399080429,
"nll": 0.23796944939572306,
"ordinalAbsoluteError": 0.2968750700820227
},
{
"id": "ru-public-4-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8132974929592196,
"probabilities": [
0.07240607967110393,
0.8132974929592196,
0.11429642736967646
],
"target": 1,
"brier": 0.05316413981812263,
"nll": 0.20665831636768178
},
{
"id": "ru-public-4-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.990562541410327,
"probabilities": [
0.990562541410327,
0.009437458589673042
],
"target": 0,
"brier": 0.00017813124926358698,
"nll": 0.009482273584633313
},
{
"id": "ru-public-4-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.914102693962366,
"probabilities": [
0.914102693962366,
0.050261625280863614,
0.03563568075677039
],
"target": 0,
"brier": 0.011174479903395361,
"nll": 0.08981235720673521,
"ordinalAbsoluteError": 0.1215329867944044
},
{
"id": "ru-public-4-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7432527985127448,
"probabilities": [
0.16072500710040374,
0.09602219438685146,
0.7432527985127448
],
"target": 2,
"brier": 0.10097191519382831,
"nll": 0.29671905187355485
},
{
"id": "ru-public-4-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9841458555310965,
"probabilities": [
0.9841458555310965,
0.01585414446890354
],
"target": 0,
"brier": 0.0005027077936817295,
"nll": 0.01598116574869607
},
{
"id": "ru-public-4-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.5251925744173698,
"probabilities": [
0.3474782510840372,
0.5251925744173698,
0.12732917449859305
],
"target": 1,
"brier": 0.3623959450433193,
"nll": 0.6439902752342354,
"ordinalAbsoluteError": 0.22014907658544414
},
{
"id": "ru-public-4-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8453846447857523,
"probabilities": [
0.8453846447857523,
0.04128928421006673,
0.11332607100418104
],
"target": 0,
"brier": 0.03845351142785236,
"nll": 0.1679635542675925
},
{
"id": "ru-public-4-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8215571641921997,
"probabilities": [
0.1784428358078003,
0.8215571641921997
],
"target": 1,
"brier": 0.06368369130225915,
"nll": 0.19655375878612552
},
{
"id": "ru-public-4-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7440381424415665,
"probabilities": [
0.15302487751767405,
0.7440381424415665,
0.10293698004075945
],
"target": 1,
"brier": 0.09952910752397465,
"nll": 0.29566297874060304,
"ordinalAbsoluteError": 0.050087897476914556
},
{
"id": "ru-public-4-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8210191237319038,
"probabilities": [
0.06607471012623846,
0.8210191237319038,
0.11290616614185774
],
"target": 1,
"brier": 0.04914782374081479,
"nll": 0.19720887658308203
},
{
"id": "ru-public-4-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7026131749153137,
"probabilities": [
0.2973868250846863,
0.7026131749153137
],
"target": 1,
"brier": 0.17687784746789958,
"nll": 0.3529487876676471
},
{
"id": "ru-public-4-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8342334752415639,
"probabilities": [
0.10196704569409856,
0.8342334752415639,
0.0637994790643376
],
"target": 1,
"brier": 0.041946192666952445,
"nll": 0.18124196946824292,
"ordinalAbsoluteError": 0.03816756662976095
},
{
"id": "ru-public-5-0",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8015487014901184,
"probabilities": [
0.8015487014901184,
0.06424655621692785,
0.13420474229295382
],
"target": 0,
"brier": 0.061521450719911164,
"nll": 0.22120954584637142
},
{
"id": "ru-public-5-0",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7528170943260193,
"probabilities": [
0.2471829056739807,
0.7528170943260193
],
"target": 1,
"brier": 0.12219877771486409,
"nll": 0.2839329833093517
},
{
"id": "ru-public-5-0",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.486454039812088,
"probabilities": [
0.3253273069858551,
0.18821865320205688,
0.486454039812088
],
"target": 2,
"brier": 0.40499357130918945,
"nll": 0.7206128529141521,
"ordinalAbsoluteError": 0.8388732671737671
},
{
"id": "ru-public-5-1",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7516253254581098,
"probabilities": [
0.08496525503850333,
0.7516253254581098,
0.16340941950338694
],
"target": 1,
"brier": 0.0956117118999817,
"nll": 0.2855173166165313
},
{
"id": "ru-public-5-1",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8752560615539551,
"probabilities": [
0.12474393844604492,
0.8752560615539551
],
"target": 1,
"brier": 0.03112210035806129,
"nll": 0.13323879365982644
},
{
"id": "ru-public-5-1",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.6956938116459195,
"probabilities": [
0.18073538484380797,
0.12357080351027261,
0.6956938116459195
],
"target": 2,
"brier": 0.1405372790854029,
"nll": 0.3628456412395528,
"ordinalAbsoluteError": 0.48504157319788854
},
{
"id": "ru-public-5-2",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7525936365127563,
"probabilities": [
0.10942308604717255,
0.1379832774400711,
0.7525936365127563
],
"target": 2,
"brier": 0.09222270530717269,
"nll": 0.28422985619636715
},
{
"id": "ru-public-5-2",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8710149675607681,
"probabilities": [
0.8710149675607681,
0.12898503243923187
],
"target": 0,
"brier": 0.0332742771866994,
"nll": 0.13809611793656218
},
{
"id": "ru-public-5-2",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7548111227267311,
"probabilities": [
0.7548111227267311,
0.14885295040291843,
0.09633592687035043
],
"target": 0,
"brier": 0.09155539718814931,
"nll": 0.28128772960435594,
"ordinalAbsoluteError": 0.3415248041436193
},
{
"id": "ru-public-5-3",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7885099044822085,
"probabilities": [
0.7885099044822085,
0.0665879746219497,
0.14490212089584179
],
"target": 0,
"brier": 0.07015864350649115,
"nll": 0.2376103114883616
},
{
"id": "ru-public-5-3",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9787534102797508,
"probabilities": [
0.9787534102797508,
0.021246589720249176
],
"target": 0,
"brier": 0.0009028351494811959,
"nll": 0.021475547361609934
},
{
"id": "ru-public-5-3",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9089698703383955,
"probabilities": [
0.9089698703383955,
0.047325207702361476,
0.04370492195924308
],
"target": 0,
"brier": 0.01243627999374371,
"nll": 0.0954433312963563,
"ordinalAbsoluteError": 0.13473505162084765
},
{
"id": "ru-public-5-4",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7495223544751545,
"probabilities": [
0.08215894927864004,
0.7495223544751545,
0.16831869624620543
],
"target": 1,
"brier": 0.09782032736026268,
"nll": 0.28831913603349335
},
{
"id": "ru-public-5-4",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.9793825875967741,
"probabilities": [
0.9793825875967741,
0.0206174124032259
],
"target": 0,
"brier": 0.0008501553884093863,
"nll": 0.020832918515239416
},
{
"id": "ru-public-5-4",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.539376195226787,
"probabilities": [
0.3700270923225053,
0.539376195226787,
0.0905967124507076
],
"target": 1,
"brier": 0.3573021028832751,
"nll": 0.6173420011992067,
"ordinalAbsoluteError": 0.27943037987179775
},
{
"id": "ru-public-5-5",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7894720670423527,
"probabilities": [
0.10496010944128363,
0.10556782351636361,
0.7894720670423527
],
"target": 2,
"brier": 0.06648320049132796,
"nll": 0.23639082647934825
},
{
"id": "ru-public-5-5",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8429958820343018,
"probabilities": [
0.15700411796569824,
0.8429958820343018
],
"target": 1,
"brier": 0.04930058611637378,
"nll": 0.17079320588627944
},
{
"id": "ru-public-5-5",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7658534531913184,
"probabilities": [
0.16132889447616197,
0.7658534531913184,
0.0728176523325197
],
"target": 1,
"brier": 0.08615402806655045,
"nll": 0.26676444191612164,
"ordinalAbsoluteError": 0.08851124214364225
},
{
"id": "ru-public-5-6",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8027474463600095,
"probabilities": [
0.8027474463600095,
0.06427180165659938,
0.13298075198339115
],
"target": 0,
"brier": 0.060723314803750775,
"nll": 0.21971512713247915
},
{
"id": "ru-public-5-6",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.732366144657135,
"probabilities": [
0.267633855342865,
0.732366144657135
],
"target": 1,
"brier": 0.14325576105137117,
"nll": 0.3114746924589172
},
{
"id": "ru-public-5-6",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.889461497491367,
"probabilities": [
0.08059104147215373,
0.889461497491367,
0.02994746103647922
],
"target": 1,
"brier": 0.0196105269249489,
"nll": 0.11713905837648149,
"ordinalAbsoluteError": 0.05064358043567452
},
{
"id": "ru-public-5-7",
"question": "action",
"type": "choice",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.7462531757447158,
"probabilities": [
0.08716081633059346,
0.7462531757447158,
0.16658600792469067
],
"target": 1,
"brier": 0.09973535675934261,
"nll": 0.29269035868007093
},
{
"id": "ru-public-5-7",
"question": "enough",
"type": "noul",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.8169542551040649,
"probabilities": [
0.18304574489593506,
0.8169542551040649
],
"target": 1,
"brier": 0.06701148944901547,
"nll": 0.20217217699439985
},
{
"id": "ru-public-5-7",
"question": "level",
"type": "score",
"source": "authored-russian-typed",
"error": null,
"correct": true,
"confidence": 0.4476746787685566,
"probabilities": [
0.352831489888138,
0.1994938313433054,
0.4476746787685566
],
"target": 2,
"brier": 0.46935110947413156,
"nll": 0.8036884738145909,
"ordinalAbsoluteError": 0.9051568111195814
}
]