diff --git "a/metrics.json" "b/metrics.json" new file mode 100644--- /dev/null +++ "b/metrics.json" @@ -0,0 +1,2599 @@ +{ + "micro_label_micro_doc": { + "class_binary": { + "accuracy": 0.8599348534201955, + "precision_entailment": 0.8930232558139535, + "recall_entailment": 0.9056603773584906, + "f1_entailment": 0.8992974238875878, + "precision_contradiction": 0.782608695652174, + "recall_contradiction": 0.7578947368421053, + "f1_contradiction": 0.7700534759358288, + "precision_mean": 0.8378159757330637, + "precision_hmean": 0.8341781317885589, + "recall_mean": 0.8317775571002979, + "recall_hmean": 0.8252148997134671, + "f1_mean": 0.8346754499117084, + "f1_hmean": 0.829672308246309 + }, + "class": { + "accuracy": 0.8505303760848602, + "precision_entailment": 0.9005964214711729, + "recall_entailment": 0.8728323699421965, + "f1_entailment": 0.8864970645792563, + "precision_contradiction": 0.6590909090909091, + "recall_contradiction": 0.6105263157894737, + "f1_contradiction": 0.633879781420765, + "precision_mean": 0.779843665281041, + "precision_hmean": 0.7611460355166718, + "recall_mean": 0.741679342865835, + "recall_hmean": 0.718487222609623, + "f1_mean": 0.7601884230000107, + "f1_hmean": 0.7392016880604888 + }, + "span": { + "precision": 0.8369565217391305, + "recall": 0.6270358306188925, + "f1": 0.7169459962756052, + "accuracy": 0.9889653169748998, + "roc_auc": 0.9814035483608237, + "map": 0.77580971867425, + "precision@recall80": 0.6309370988446726, + "precision@recall90": 0.3544871794871795, + "precision@1": 0.8827361563517915, + "recall@1": 0.44136807817589574, + "f1@1": 0.5884907709011944, + "accuracy@1": 0.9862429445180493, + "precision@3": 0.5162866449511401, + "recall@3": 0.7744299674267101, + "f1@3": 0.6195439739413681, + "accuracy@3": 0.9788017931359916, + "precision@5": 0.34755700325732897, + "recall@5": 0.8688925081433225, + "f1@5": 0.49651000465332706, + "accuracy@5": 0.9607252400225049, + "precision@8": 0.2296416938110749, + "recall@8": 0.9185667752442996, + "f1@8": 0.3674267100977199, + "accuracy@8": 0.929508702517287, + "precision@10": 0.18745928338762216, + "recall@10": 0.9372964169381107, + "f1@10": 0.3124321389793703, + "accuracy@10": 0.908056407557306, + "precision@15": 0.12833876221498372, + "recall@15": 0.9625407166123778, + "f1@15": 0.22648016861467718, + "accuracy@15": 0.8534637652225994, + "precision@20": 0.09723127035830618, + "recall@20": 0.9723127035830619, + "f1@20": 0.17678412792419304, + "accuracy@20": 0.7981814551988239, + "precision@30": 0.0664400833241969, + "recall@30": 0.9869706840390879, + "f1@30": 0.12449922958397534, + "accuracy@30": 0.690629594003521, + "precision@40": 0.050884217550884216, + "recall@40": 0.993485342019544, + "f1@40": 0.09681003015394382, + "accuracy@40": 0.5868527559483838, + "precision@50": 0.04172769697176142, + "recall@50": 0.997557003257329, + "f1@50": 0.08010462645087463, + "accuracy@50": 0.4893736728434273 + } + }, + "macro_label_micro_doc": { + "class_binary": { + "accuracy": 0.8233394157923417, + "precision_entailment": 0.7415170815819401, + "recall_entailment": 0.7835695006747638, + "f1_entailment": 0.7486184750529762, + "precision_contradiction": 0.49699494949494954, + "recall_contradiction": 0.4251488095238095, + "f1_contradiction": 0.4103942924687606, + "precision_mean": 0.6192560155384448, + "precision_hmean": 0.3730127874750814, + "recall_mean": 0.6043591550992866, + "recall_hmean": 0.30291954497850543, + "f1_mean": 0.5795063837608684, + "f1_hmean": 0.32125044837060795 + }, + "class": { + "accuracy": 0.8505303760848602, + "precision_entailment": 0.815405627487823, + "recall_entailment": 0.7947278055663506, + "f1_entailment": 0.7930728914489584, + "precision_contradiction": 0.14706421029950442, + "recall_contradiction": 0.3253517316017316, + "f1_contradiction": 0.2973370927318295, + "precision_mean": 0.48123491889366365, + "precision_hmean": 0.10900261033205852, + "recall_mean": 0.5100189150518097, + "recall_hmean": 0.23527542091124293, + "f1_mean": 0.48426389055722524, + "f1_hmean": 0.22324263654086207 + }, + "span": { + "precision": 0.8362480298845821, + "recall": 0.6151578745970415, + "f1": 0.6994116433432479, + "accuracy": 0.9888179275403737, + "roc_auc": 0.9803877913182639, + "map": 0.7744164612173341, + "precision@recall80": 0.6006178606957627, + "precision@recall90": 0.3603357137412647, + "precision@1": 0.8647391296349896, + "recall@1": 0.4525946585647953, + "f1@1": 0.5870524047730916, + "accuracy@1": 0.9860614675046785, + "precision@3": 0.5079871008936006, + "recall@3": 0.7740116460932431, + "f1@3": 0.6061788054644821, + "accuracy@3": 0.9781581510295619, + "precision@5": 0.346197577755079, + "recall@5": 0.8718429410389403, + "f1@5": 0.4907425369921605, + "accuracy@5": 0.9603001613816903, + "precision@8": 0.22902806293396008, + "recall@8": 0.9200965979492031, + "f1@8": 0.36402337519274897, + "accuracy@8": 0.9289343733019633, + "precision@10": 0.18708803806711685, + "recall@10": 0.9388527199556923, + "f1@10": 0.30998352705023713, + "accuracy@10": 0.9073741064486206, + "precision@15": 0.12819735938655383, + "recall@15": 0.9643159258869369, + "f1@15": 0.2252173563453309, + "accuracy@15": 0.8525192128019405, + "precision@20": 0.09718739190465374, + "recall@20": 0.9739997099721253, + "f1@20": 0.17606156913724372, + "accuracy@20": 0.7969858576859808, + "precision@30": 0.06630076771492631, + "recall@30": 0.9877342310746402, + "f1@30": 0.12393783344968093, + "accuracy@30": 0.6891550447915792, + "precision@40": 0.050684493547513615, + "recall@40": 0.9942662988752936, + "f1@40": 0.09626424105991742, + "accuracy@40": 0.5846773767204779, + "precision@50": 0.04152704331410473, + "recall@50": 0.9977923095812351, + "f1@50": 0.07960577431988926, + "accuracy@50": 0.48644684876867916 + } + }, + "macro_label_macro_doc": { + "span": { + "precision": 0.7144376184887653, + "recall": 0.6523323090619284, + "f1": 0.6532976465075738, + "accuracy": 0.9868885256696579, + "roc_auc": 0.9860789157437274, + "map": 0.8702873539874406, + "precision@recall80": 0.8220029735884278, + "precision@recall90": 0.8114087660105708, + "precision@1": 0.8647391296349896, + "recall@1": 0.5724841132981842, + "f1@1": 0.6516399468995943, + "accuracy@1": 0.9845202173700275, + "precision@3": 0.5079871008936007, + "recall@3": 0.8583862333239409, + "f1@3": 0.5948583304266755, + "accuracy@3": 0.9716733706320901, + "precision@5": 0.346197577755079, + "recall@5": 0.9234314632376149, + "f1@5": 0.4690116960547623, + "accuracy@5": 0.9471229075988444, + "precision@8": 0.22902806293396008, + "recall@8": 0.9518947258374904, + "f1@8": 0.3467702095669957, + "accuracy@8": 0.9056371606296331, + "precision@10": 0.18708803806711674, + "recall@10": 0.9627708618079199, + "f1@10": 0.2959430988348894, + "accuracy@10": 0.8774175550745262, + "precision@15": 0.12819735938655383, + "recall@15": 0.9814406668896785, + "f1@15": 0.2167246953930399, + "accuracy@15": 0.8058007171797139, + "precision@20": 0.09718739190465374, + "recall@20": 0.9883583460138484, + "f1@20": 0.17049080172218162, + "accuracy@20": 0.7332341010794474, + "precision@30": 0.06631452781330305, + "recall@30": 0.9947426503081701, + "f1@30": 0.12099922690676244, + "accuracy@30": 0.6018917921509874, + "precision@40": 0.05088869737369972, + "recall@40": 0.9975175186492364, + "f1@40": 0.09477697771441906, + "accuracy@40": 0.4805109676095023, + "precision@50": 0.041934097675195695, + "recall@50": 0.9991766650121842, + "f1@50": 0.07906913670211999, + "accuracy@50": 0.3736541811705555 + } + }, + "micro_label_macro_doc": { + "class": { + "accuracy": 0.8505303760848599, + "precision_entailment": 0.898413153331186, + "recall_entailment": 0.8574977845469647, + "f1_entailment": 0.8705066648306693, + "precision_contradiction": 0.5245901639344263, + "recall_contradiction": 0.5880503144654088, + "f1_contradiction": 0.5689128481581313, + "precision_mean": 0.7115016586328058, + "precision_hmean": 0.5395411138245387, + "recall_mean": 0.7300424680141662, + "recall_hmean": 0.5981284032240637, + "f1_mean": 0.7225707406808176, + "f1_hmean": 0.5983586026722526 + }, + "span": { + "precision": 0.7237804405149684, + "recall": 0.6627035830618895, + "f1": 0.6648658254521455, + "accuracy": 0.9869977376799727, + "roc_auc": 0.9867290995620759, + "map": 0.8815333602793199, + "precision@recall80": 0.8331544835380537, + "precision@recall90": 0.8222580301767375, + "precision@1": 0.8827361563517915, + "recall@1": 0.5796268290160794, + "f1@1": 0.6629893631522311, + "accuracy@1": 0.9848010997685606, + "precision@3": 0.516286644951141, + "recall@3": 0.8686986195129518, + "f1@3": 0.6058808907343124, + "accuracy@3": 0.9724472602576117, + "precision@5": 0.34755700325732775, + "recall@5": 0.923403650276615, + "f1@5": 0.47219853978811727, + "accuracy@5": 0.9472914942490297, + "precision@8": 0.2296416938110749, + "recall@8": 0.953303862261517, + "f1@8": 0.3487310905015473, + "accuracy@8": 0.9055414320616549, + "precision@10": 0.1874592833876214, + "recall@10": 0.9639580425003879, + "f1@10": 0.297276817682398, + "accuracy@10": 0.8771142021736739, + "precision@15": 0.1283387622149846, + "recall@15": 0.9800197766402978, + "f1@15": 0.2172754679895953, + "accuracy@15": 0.8050377490508176, + "precision@20": 0.09723127035830581, + "recall@20": 0.9873532909363528, + "f1@20": 0.17078721955881296, + "accuracy@20": 0.7321110475501871, + "precision@30": 0.06640213513531784, + "recall@30": 0.9943992037640247, + "f1@30": 0.12125877843950333, + "accuracy@30": 0.5999768714479196, + "precision@40": 0.051009552580682606, + "recall@40": 0.9971860296778864, + "f1@40": 0.09505578091587771, + "accuracy@40": 0.4791097187920494, + "precision@50": 0.04209138601718905, + "recall@50": 0.9990047050307637, + "f1@50": 0.07939158056921974, + "accuracy@50": 0.3726312058346531 + } + }, + "label_wise": { + "nda-1": { + "micro_doc": { + "class_binary": { + "accuracy": 0.5862068965517241, + "precision_entailment": 0.8181818181818182, + "recall_entailment": 0.47368421052631576, + "f1_entailment": 0.6, + "precision_contradiction": 0.4444444444444444, + "recall_contradiction": 0.8, + "f1_contradiction": 0.5714285714285714, + "precision_mean": 0.6313131313131313, + "precision_hmean": 0.576, + "recall_mean": 0.6368421052631579, + "recall_hmean": 0.5950413223140496, + "f1_mean": 0.5857142857142856, + "f1_hmean": 0.5853658536585366 + }, + "class": { + "accuracy": 0.7377049180327869, + "precision_entailment": 0.8, + "recall_entailment": 0.42105263157894735, + "f1_entailment": 0.5517241379310345, + "precision_contradiction": 0.3333333333333333, + "recall_contradiction": 0.5, + "f1_contradiction": 0.4, + "precision_mean": 0.5666666666666667, + "precision_hmean": 0.47058823529411764, + "recall_mean": 0.4605263157894737, + "recall_hmean": 0.45714285714285713, + "f1_mean": 0.47586206896551725, + "f1_hmean": 0.463768115942029 + }, + "span": { + "precision": 0.6382978723404256, + "recall": 0.5172413793103449, + "f1": 0.5714285714285714, + "accuracy": 0.9836065573770492, + "roc_auc": 0.9736983945689975, + "map": 0.6344776019891116, + "precision@recall80": 0.2640449438202247, + "precision@recall90": 0.21544715447154472, + "precision@1": 0.6896551724137931, + "recall@1": 0.3448275862068966, + "f1@1": 0.4597701149425288, + "accuracy@1": 0.9828779599271402, + "precision@3": 0.4482758620689655, + "recall@3": 0.6724137931034483, + "f1@3": 0.5379310344827587, + "accuracy@3": 0.975591985428051, + "precision@5": 0.33793103448275863, + "recall@5": 0.8448275862068966, + "f1@5": 0.48275862068965514, + "accuracy@5": 0.9617486338797814, + "precision@8": 0.22413793103448276, + "recall@8": 0.896551724137931, + "f1@8": 0.35862068965517246, + "accuracy@8": 0.9322404371584699, + "precision@10": 0.18620689655172415, + "recall@10": 0.9310344827586207, + "f1@10": 0.3103448275862069, + "accuracy@10": 0.912568306010929, + "precision@15": 0.1310344827586207, + "recall@15": 0.9827586206896551, + "f1@15": 0.23123732251521303, + "accuracy@15": 0.8619307832422587, + "precision@20": 0.09827586206896552, + "recall@20": 0.9827586206896551, + "f1@20": 0.1786833855799373, + "accuracy@20": 0.8091074681238616, + "precision@30": 0.06620209059233449, + "recall@30": 0.9827586206896551, + "f1@30": 0.12404787812840043, + "accuracy@30": 0.7067395264116576, + "precision@40": 0.051418439716312055, + "recall@40": 1.0, + "f1@40": 0.09780775716694773, + "accuracy@40": 0.6102003642987249, + "precision@50": 0.04187725631768953, + "recall@50": 1.0, + "f1@50": 0.08038808038808039, + "accuracy@50": 0.516575591985428 + } + }, + "macro_doc": { + "span": { + "precision": 0.4781609195402298, + "recall": 0.553448275862069, + "f1": 0.47432950191570883, + "accuracy": 0.9800445986258561, + "roc_auc": 0.9810151363715633, + "map": 0.7806573933729105, + "precision@recall80": 0.7567849774746327, + "precision@recall90": 0.7323017978190391, + "precision@1": 0.6896551724137931, + "recall@1": 0.45948275862068966, + "f1@1": 0.5175150519978106, + "accuracy@1": 0.9787551183163938, + "precision@3": 0.44827586206896547, + "recall@3": 0.782183908045977, + "f1@3": 0.5236229287953426, + "accuracy@3": 0.9681379680627418, + "precision@5": 0.3379310344827586, + "recall@5": 0.9109195402298851, + "f1@5": 0.4498289067254585, + "accuracy@5": 0.9469066902249391, + "precision@8": 0.22413793103448276, + "recall@8": 0.925287356321839, + "f1@8": 0.33145877111394345, + "accuracy@8": 0.9060893797474374, + "precision@10": 0.18620689655172412, + "recall@10": 0.9382183908045977, + "f1@10": 0.2872304898166967, + "accuracy@10": 0.8790554006820582, + "precision@15": 0.13103448275862073, + "recall@15": 0.9942528735632183, + "f1@15": 0.21753729504111283, + "accuracy@15": 0.8088716887455585, + "precision@20": 0.0982758620689655, + "recall@20": 0.9942528735632183, + "f1@20": 0.16995178734309166, + "accuracy@20": 0.7361540401574757, + "precision@30": 0.06650246305418722, + "recall@30": 0.9942528735632183, + "f1@30": 0.12009752077691864, + "accuracy@30": 0.6054970681044621, + "precision@40": 0.05189860426929392, + "recall@40": 1.0, + "f1@40": 0.0957740117892033, + "accuracy@40": 0.491073862285215, + "precision@50": 0.04267630052754777, + "recall@50": 1.0, + "f1@50": 0.07984782905069218, + "accuracy@50": 0.38488803232073165 + } + } + }, + "nda-10": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.8524590163934426, + "precision_entailment": 0.8571428571428571, + "recall_entailment": 0.8275862068965517, + "f1_entailment": 0.8421052631578947, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.42857142857142855, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.8392857142857143, + "recall": 0.7014925373134329, + "f1": 0.7642276422764228, + "accuracy": 0.9888160431932125, + "roc_auc": 0.9840996915659233, + "map": 0.8353220491439133, + "precision@recall80": 0.6923076923076923, + "precision@recall90": 0.5, + "precision@1": 0.7931034482758621, + "recall@1": 0.34328358208955223, + "f1@1": 0.4791666666666667, + "accuracy@1": 0.9807173158503664, + "precision@3": 0.5172413793103449, + "recall@3": 0.6716417910447762, + "f1@3": 0.5844155844155844, + "accuracy@3": 0.975318164288469, + "precision@5": 0.3793103448275862, + "recall@5": 0.8208955223880597, + "f1@5": 0.5188679245283019, + "accuracy@5": 0.9606633243347474, + "precision@8": 0.27586206896551724, + "recall@8": 0.9552238805970149, + "f1@8": 0.42809364548494977, + "accuracy@8": 0.934053220208253, + "precision@10": 0.2206896551724138, + "recall@10": 0.9552238805970149, + "f1@10": 0.3585434173669467, + "accuracy@10": 0.911685306594678, + "precision@15": 0.1471264367816092, + "recall@15": 0.9552238805970149, + "f1@15": 0.2549800796812749, + "accuracy@15": 0.8557655225607405, + "precision@20": 0.11206896551724138, + "recall@20": 0.9701492537313433, + "f1@20": 0.20092735703245748, + "accuracy@20": 0.8006170458927883, + "precision@30": 0.07549361207897794, + "recall@30": 0.9701492537313433, + "f1@30": 0.14008620689655174, + "accuracy@30": 0.6922483609718473, + "precision@40": 0.058098591549295774, + "recall@40": 0.9850746268656716, + "f1@40": 0.10972568578553617, + "accuracy@40": 0.5869649055148477, + "precision@50": 0.04775687409551375, + "recall@50": 0.9850746268656716, + "f1@50": 0.09109730848861283, + "accuracy@50": 0.49209409949865024 + } + }, + "macro_doc": { + "span": { + "precision": 0.6746715927750409, + "recall": 0.6874794745484402, + "f1": 0.6565134099616858, + "accuracy": 0.9873366365635738, + "roc_auc": 0.9924945777159988, + "map": 0.8616180161716547, + "precision@recall80": 0.8346595932802828, + "precision@recall90": 0.8138318481208833, + "precision@1": 0.7931034482758621, + "recall@1": 0.5536261631089218, + "f1@1": 0.6007662835249041, + "accuracy@1": 0.9817597772978593, + "precision@3": 0.517241379310345, + "recall@3": 0.885016420361248, + "f1@3": 0.572257053291536, + "accuracy@3": 0.9704154507660806, + "precision@5": 0.37931034482758613, + "recall@5": 0.9451423097974823, + "f1@5": 0.4674940002526211, + "accuracy@5": 0.9471614846323319, + "precision@8": 0.27586206896551724, + "recall@8": 0.9885057471264367, + "f1@8": 0.37542187359631574, + "accuracy@8": 0.908699662822764, + "precision@10": 0.22068965517241376, + "recall@10": 0.9885057471264367, + "f1@10": 0.31845261128916513, + "accuracy@10": 0.8793846182937739, + "precision@15": 0.1471264367816092, + "recall@15": 0.9885057471264367, + "f1@15": 0.23200632304168772, + "accuracy@15": 0.8060970069712986, + "precision@20": 0.11206896551724137, + "recall@20": 0.9923371647509579, + "f1@20": 0.18536104888790614, + "accuracy@20": 0.7331525076748997, + "precision@30": 0.07520525451559934, + "recall@30": 0.9923371647509579, + "f1@30": 0.13162067238965544, + "accuracy@30": 0.6013556101531022, + "precision@40": 0.05779967159277503, + "recall@40": 0.9961685823754789, + "f1@40": 0.10415547103122826, + "accuracy@40": 0.4764699691565601, + "precision@50": 0.04735141362523572, + "recall@50": 0.9961685823754789, + "f1@50": 0.0870171523118904, + "accuracy@50": 0.3757081508777044 + } + } + }, + "nda-11": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.9672131147540983, + "precision_entailment": 1.0, + "recall_entailment": 0.75, + "f1_entailment": 0.8571428571428571, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.5, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 1.0, + "recall": 0.6666666666666666, + "f1": 0.8, + "accuracy": 0.9945454545454545, + "roc_auc": 0.9683713288149518, + "map": 0.7864386495338878, + "precision@recall80": 0.1111111111111111, + "precision@recall90": 0.09183673469387756, + "precision@1": 0.75, + "recall@1": 0.6666666666666666, + "f1@1": 0.7058823529411765, + "accuracy@1": 0.990909090909091, + "precision@3": 0.3333333333333333, + "recall@3": 0.8888888888888888, + "f1@3": 0.48484848484848486, + "accuracy@3": 0.9690909090909091, + "precision@5": 0.225, + "recall@5": 1.0, + "f1@5": 0.36734693877551017, + "accuracy@5": 0.9436363636363636, + "precision@8": 0.140625, + "recall@8": 1.0, + "f1@8": 0.2465753424657534, + "accuracy@8": 0.9, + "precision@10": 0.1125, + "recall@10": 1.0, + "f1@10": 0.20224719101123595, + "accuracy@10": 0.8709090909090909, + "precision@15": 0.075, + "recall@15": 1.0, + "f1@15": 0.13953488372093023, + "accuracy@15": 0.7981818181818182, + "precision@20": 0.05625, + "recall@20": 1.0, + "f1@20": 0.10650887573964499, + "accuracy@20": 0.7254545454545455, + "precision@30": 0.03896103896103896, + "recall@30": 1.0, + "f1@30": 0.07500000000000001, + "accuracy@30": 0.5963636363636363, + "precision@40": 0.029900332225913623, + "recall@40": 1.0, + "f1@40": 0.058064516129032254, + "accuracy@40": 0.4690909090909091, + "precision@50": 0.02425876010781671, + "recall@50": 1.0, + "f1@50": 0.047368421052631574, + "accuracy@50": 0.3418181818181818 + } + }, + "macro_doc": { + "span": { + "precision": 0.75, + "recall": 0.6875, + "f1": 0.7083333333333333, + "accuracy": 0.9941621598783168, + "roc_auc": 0.9884577515216613, + "map": 0.8166666666666667, + "precision@recall80": 0.7958333333333333, + "precision@recall90": 0.7958333333333333, + "precision@1": 0.75, + "recall@1": 0.6875, + "f1@1": 0.7083333333333333, + "accuracy@1": 0.9896129795504478, + "precision@3": 0.3333333333333333, + "recall@3": 0.875, + "f1@3": 0.475, + "accuracy@3": 0.95956491238052, + "precision@5": 0.22499999999999998, + "recall@5": 1.0, + "f1@5": 0.3630952380952382, + "accuracy@5": 0.9260378862787007, + "precision@8": 0.140625, + "recall@8": 1.0, + "f1@8": 0.24444444444444446, + "accuracy@8": 0.8695998061423656, + "precision@10": 0.11249999999999999, + "recall@10": 1.0, + "f1@10": 0.2007575757575758, + "accuracy@10": 0.8319744193848086, + "precision@15": 0.075, + "recall@15": 1.0, + "f1@15": 0.13878676470588236, + "accuracy@15": 0.7379109524909166, + "precision@20": 0.056249999999999994, + "recall@20": 1.0, + "f1@20": 0.10606060606060606, + "accuracy@20": 0.6438474855970246, + "precision@30": 0.039285714285714285, + "recall@30": 1.0, + "f1@30": 0.07537573313782991, + "accuracy@30": 0.5092919803806691, + "precision@40": 0.03095238095238095, + "recall@40": 1.0, + "f1@40": 0.059853764122056806, + "accuracy@40": 0.3806888561166946, + "precision@50": 0.025952380952380952, + "recall@50": 1.0, + "f1@50": 0.050390785684903336, + "accuracy@50": 0.25208573185272015 + } + } + }, + "nda-12": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.9672131147540983, + "precision_entailment": 1.0, + "recall_entailment": 0.95, + "f1_entailment": 0.9743589743589743, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.5, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.975, + "recall": 0.7722772277227723, + "f1": 0.861878453038674, + "accuracy": 0.993109151047409, + "roc_auc": 0.9899754931546458, + "map": 0.901206991750224, + "precision@recall80": 0.9642857142857143, + "precision@recall90": 0.4008810572687225, + "precision@1": 1.0, + "recall@1": 0.39603960396039606, + "f1@1": 0.5673758865248227, + "accuracy@1": 0.9831863285556781, + "precision@3": 0.7083333333333334, + "recall@3": 0.8415841584158416, + "f1@3": 0.7692307692307693, + "accuracy@3": 0.9859426681367145, + "precision@5": 0.47, + "recall@5": 0.9306930693069307, + "f1@5": 0.6245847176079734, + "accuracy@5": 0.9688533627342889, + "precision@8": 0.296875, + "recall@8": 0.9405940594059405, + "f1@8": 0.45130641330166277, + "accuracy@8": 0.9363285556780595, + "precision@10": 0.2375, + "recall@10": 0.9405940594059405, + "f1@10": 0.37924151696606784, + "accuracy@10": 0.9142778390297684, + "precision@15": 0.165, + "recall@15": 0.9801980198019802, + "f1@15": 0.28245363766048504, + "accuracy@15": 0.8613561190738699, + "precision@20": 0.12625, + "recall@20": 1.0, + "f1@20": 0.2241953385127636, + "accuracy@20": 0.8073318632855567, + "precision@30": 0.08480268681780016, + "recall@30": 1.0, + "f1@30": 0.15634674922600617, + "accuracy@30": 0.6995589856670342, + "precision@40": 0.06441326530612244, + "recall@40": 1.0, + "f1@40": 0.12103055721989214, + "accuracy@40": 0.5956449834619625, + "precision@50": 0.05219638242894057, + "recall@50": 1.0, + "f1@50": 0.09921414538310412, + "accuracy@50": 0.49448732083792724 + } + }, + "macro_doc": { + "span": { + "precision": 0.9324999999999999, + "recall": 0.8008928571428573, + "f1": 0.8416558441558442, + "accuracy": 0.9904970898399632, + "roc_auc": 0.99174353806044, + "map": 0.9496897072226019, + "precision@recall80": 0.8720723684210526, + "precision@recall90": 0.859875398724083, + "precision@1": 1.0, + "recall@1": 0.43898809523809523, + "f1@1": 0.6017261904761906, + "accuracy@1": 0.9796903712569248, + "precision@3": 0.7083333333333336, + "recall@3": 0.9002976190476192, + "f1@3": 0.7742857142857147, + "accuracy@3": 0.9823080804894845, + "precision@5": 0.4700000000000001, + "recall@5": 0.9511904761904763, + "f1@5": 0.6111201298701301, + "accuracy@5": 0.959099393674648, + "precision@8": 0.296875, + "recall@8": 0.9595238095238097, + "f1@8": 0.4422510822510824, + "accuracy@8": 0.9168312317532699, + "precision@10": 0.23750000000000004, + "recall@10": 0.9595238095238097, + "f1@10": 0.37222648674854575, + "accuracy@10": 0.888428743492485, + "precision@15": 0.1650000000000001, + "recall@15": 0.9833333333333334, + "f1@15": 0.2768064323017882, + "accuracy@15": 0.8200819545073257, + "precision@20": 0.12625, + "recall@20": 1.0, + "f1@20": 0.22045004110221494, + "accuracy@20": 0.7504859902656202, + "precision@30": 0.08488095238095243, + "recall@30": 1.0, + "f1@30": 0.15456040497600596, + "accuracy@30": 0.6191878346759826, + "precision@40": 0.06474702380952381, + "recall@40": 1.0, + "f1@40": 0.12043161100058561, + "accuracy@40": 0.4989015838482495, + "precision@50": 0.05293585359675788, + "recall@50": 1.0, + "f1@50": 0.09969918158461984, + "accuracy@50": 0.3853450062727963 + } + } + }, + "nda-13": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 1.0, + "precision_entailment": 1.0, + "recall_entailment": 1.0, + "f1_entailment": 1.0, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.5, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.9583333333333334, + "recall": 0.7603305785123967, + "f1": 0.8479262672811061, + "accuracy": 0.9923058988109116, + "roc_auc": 0.9919040782982503, + "map": 0.8889136129849528, + "precision@recall80": 0.9150943396226415, + "precision@recall90": 0.44672131147540983, + "precision@1": 0.9787234042553191, + "recall@1": 0.38016528925619836, + "f1@1": 0.5476190476190476, + "accuracy@1": 0.982280251806948, + "precision@3": 0.7021276595744681, + "recall@3": 0.8181818181818182, + "f1@3": 0.7557251908396947, + "accuracy@3": 0.9850781067847983, + "precision@5": 0.4595744680851064, + "recall@5": 0.8925619834710744, + "f1@5": 0.6067415730337079, + "accuracy@5": 0.9673583585917463, + "precision@8": 0.29521276595744683, + "recall@8": 0.9173553719008265, + "f1@8": 0.44668008048289737, + "accuracy@8": 0.9358824900909303, + "precision@10": 0.24680851063829787, + "recall@10": 0.9586776859504132, + "f1@10": 0.3925549915397631, + "accuracy@10": 0.9162975052459781, + "precision@15": 0.16879432624113475, + "recall@15": 0.9834710743801653, + "f1@15": 0.288135593220339, + "accuracy@15": 0.8629051060853346, + "precision@20": 0.1276595744680851, + "recall@20": 0.9917355371900827, + "f1@20": 0.22620169651272384, + "accuracy@20": 0.808580088598741, + "precision@30": 0.08636688079942897, + "recall@30": 1.0, + "f1@30": 0.1590013140604468, + "accuracy@30": 0.7015621356959664, + "precision@40": 0.06547619047619048, + "recall@40": 1.0, + "f1@40": 0.1229050279329609, + "accuracy@40": 0.5973420377710422, + "precision@50": 0.053023663453111304, + "recall@50": 1.0, + "f1@50": 0.10070744902205575, + "accuracy@50": 0.4961529494054558 + } + }, + "macro_doc": { + "span": { + "precision": 0.9716312056737589, + "recall": 0.8417173252279635, + "f1": 0.8779005864112246, + "accuracy": 0.9910662974609143, + "roc_auc": 0.9933019669958763, + "map": 0.9441429357910898, + "precision@recall80": 0.8990667724710278, + "precision@recall90": 0.87575044202078, + "precision@1": 0.9787234042553191, + "recall@1": 0.4354863221884499, + "f1@1": 0.5934312732185075, + "accuracy@1": 0.9782484634191496, + "precision@3": 0.7021276595744684, + "recall@3": 0.8951114488348532, + "f1@3": 0.7647462466611404, + "accuracy@3": 0.9821784404441406, + "precision@5": 0.4595744680851063, + "recall@5": 0.9405268490374873, + "f1@5": 0.5969071118007293, + "accuracy@5": 0.9586434492850261, + "precision@8": 0.29521276595744683, + "recall@8": 0.9533181357649445, + "f1@8": 0.43655971687886586, + "accuracy@8": 0.9187468491833536, + "precision@10": 0.24680851063829784, + "recall@10": 0.9850557244174266, + "f1@10": 0.382917405914903, + "accuracy@10": 0.8938839758195715, + "precision@15": 0.1687943262411349, + "recall@15": 0.9943009118541033, + "f1@15": 0.2809561475356532, + "accuracy@15": 0.825903472264402, + "precision@20": 0.1276595744680851, + "recall@20": 0.9969604863221884, + "f1@20": 0.2211463939493541, + "accuracy@20": 0.7569923381739664, + "precision@30": 0.08672745694022296, + "recall@30": 1.0, + "f1@30": 0.1567306296079104, + "accuracy@30": 0.6280726694577772, + "precision@40": 0.06622340425531914, + "recall@40": 1.0, + "f1@40": 0.12233880350522207, + "accuracy@40": 0.5078897123204714, + "precision@50": 0.0542043911272069, + "recall@50": 1.0, + "f1@50": 0.10143117914308984, + "accuracy@50": 0.3947922172539155 + } + } + }, + "nda-15": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.8852459016393442, + "precision_entailment": 0.8809523809523809, + "recall_entailment": 0.9487179487179487, + "f1_entailment": 0.9135802469135802, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.44047619047619047, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.7534246575342466, + "recall": 0.8088235294117647, + "f1": 0.7801418439716311, + "accuracy": 0.9913480323751047, + "roc_auc": 0.9899673667475526, + "map": 0.7389612056955897, + "precision@recall80": 0.7534246575342466, + "precision@recall90": 0.6526315789473685, + "precision@1": 0.8717948717948718, + "recall@1": 0.5, + "f1@1": 0.6355140186915887, + "accuracy@1": 0.989115266536422, + "precision@3": 0.5213675213675214, + "recall@3": 0.8970588235294118, + "f1@3": 0.6594594594594595, + "accuracy@3": 0.982416969020374, + "precision@5": 0.3230769230769231, + "recall@5": 0.9264705882352942, + "f1@5": 0.479087452471483, + "accuracy@5": 0.9617638850125593, + "precision@8": 0.20833333333333334, + "recall@8": 0.9558823529411765, + "f1@8": 0.34210526315789475, + "accuracy@8": 0.9302260675411667, + "precision@10": 0.16923076923076924, + "recall@10": 0.9705882352941176, + "f1@10": 0.28820960698689957, + "accuracy@10": 0.9090147920736813, + "precision@15": 0.11282051282051282, + "recall@15": 0.9705882352941176, + "f1@15": 0.20214395099540583, + "accuracy@15": 0.8545911247557912, + "precision@20": 0.08717948717948718, + "recall@20": 1.0, + "f1@20": 0.16037735849056603, + "accuracy@20": 0.8012838403572425, + "precision@30": 0.059079061685490875, + "recall@30": 1.0, + "f1@30": 0.11156685808039377, + "accuracy@30": 0.6977393245883338, + "precision@40": 0.04509283819628647, + "recall@40": 1.0, + "f1@40": 0.08629441624365482, + "accuracy@40": 0.5981021490371198, + "precision@50": 0.036657681940700806, + "recall@50": 1.0, + "f1@50": 0.07072282891315652, + "accuracy@50": 0.501255930784259 + } + }, + "macro_doc": { + "span": { + "precision": 0.7778388278388279, + "recall": 0.8153846153846154, + "f1": 0.7570207570207572, + "accuracy": 0.9898434476663783, + "roc_auc": 0.9917259184838667, + "map": 0.9046547678900618, + "precision@recall80": 0.8906485671191553, + "precision@recall90": 0.8778280542986425, + "precision@1": 0.8717948717948718, + "recall@1": 0.5905982905982905, + "f1@1": 0.6752136752136754, + "accuracy@1": 0.986489428042502, + "precision@3": 0.5213675213675213, + "recall@3": 0.9256410256410255, + "f1@3": 0.6371794871794874, + "accuracy@3": 0.9762329410166302, + "precision@5": 0.3230769230769231, + "recall@5": 0.9393162393162393, + "f1@5": 0.4615995115995116, + "accuracy@5": 0.9482572148827675, + "precision@8": 0.20833333333333334, + "recall@8": 0.9606837606837607, + "f1@8": 0.33175940868248566, + "accuracy@8": 0.9050285935531326, + "precision@10": 0.16923076923076924, + "recall@10": 0.9658119658119657, + "f1@10": 0.2797800490108182, + "accuracy@10": 0.8762121780539905, + "precision@15": 0.11282051282051284, + "recall@15": 0.9658119658119657, + "f1@15": 0.1976914697502933, + "accuracy@15": 0.8024386375736328, + "precision@20": 0.08717948717948719, + "recall@20": 1.0, + "f1@20": 0.1575873401960358, + "accuracy@20": 0.7294244659295674, + "precision@30": 0.05934065934065936, + "recall@30": 1.0, + "f1@30": 0.11062324772002188, + "accuracy@30": 0.6056869087783765, + "precision@40": 0.045703601953601965, + "recall@40": 1.0, + "f1@40": 0.08650836359287865, + "accuracy@40": 0.4932436129214465, + "precision@50": 0.03765941210090148, + "recall@50": 1.0, + "f1@50": 0.07190651687151302, + "accuracy@50": 0.3877025460412138 + } + } + }, + "nda-16": { + "micro_doc": { + "class_binary": { + "accuracy": 0.9166666666666666, + "precision_entailment": 0.9166666666666666, + "recall_entailment": 1.0, + "f1_entailment": 0.9565217391304348, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.4583333333333333, + "precision_hmean": 0.0, + "recall_mean": 0.5, + "recall_hmean": 0.0, + "f1_mean": 0.4782608695652174, + "f1_hmean": 0.0 + }, + "class": { + "accuracy": 0.7868852459016393, + "precision_entailment": 0.8125, + "recall_entailment": 0.5909090909090909, + "f1_entailment": 0.6842105263157896, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.40625, + "precision_hmean": 0.0, + "recall_mean": 0.29545454545454547, + "recall_hmean": 0.0, + "f1_mean": 0.3421052631578948, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.7857142857142857, + "recall": 0.21568627450980393, + "f1": 0.3384615384615385, + "accuracy": 0.9803293687099726, + "roc_auc": 0.9647426183588189, + "map": 0.5775770462777687, + "precision@recall80": 0.2611464968152866, + "precision@recall90": 0.12169312169312169, + "precision@1": 0.875, + "recall@1": 0.4117647058823529, + "f1@1": 0.56, + "accuracy@1": 0.984903934126258, + "precision@3": 0.4861111111111111, + "recall@3": 0.6862745098039216, + "f1@3": 0.5691056910569106, + "accuracy@3": 0.9757548032936871, + "precision@5": 0.35, + "recall@5": 0.8235294117647058, + "f1@5": 0.4912280701754386, + "accuracy@5": 0.9602012808783166, + "precision@8": 0.22916666666666666, + "recall@8": 0.8627450980392157, + "f1@8": 0.3621399176954732, + "accuracy@8": 0.9290942360475755, + "precision@10": 0.18333333333333332, + "recall@10": 0.8627450980392157, + "f1@10": 0.3024054982817869, + "accuracy@10": 0.9071363220494053, + "precision@15": 0.12222222222222222, + "recall@15": 0.8627450980392157, + "f1@15": 0.2141119221411192, + "accuracy@15": 0.8522415370539799, + "precision@20": 0.09166666666666666, + "recall@20": 0.8627450980392157, + "f1@20": 0.16572504708097927, + "accuracy@20": 0.7973467520585544, + "precision@30": 0.06805555555555555, + "recall@30": 0.9607843137254902, + "f1@30": 0.12710765239948116, + "accuracy@30": 0.692131747483989, + "precision@40": 0.05268703898840885, + "recall@40": 0.9803921568627451, + "f1@40": 0.10000000000000002, + "accuracy@40": 0.5882891125343093, + "precision@50": 0.04407951598962835, + "recall@50": 1.0, + "f1@50": 0.08443708609271523, + "accuracy@50": 0.4940530649588289 + } + }, + "macro_doc": { + "span": { + "precision": 0.3333333333333333, + "recall": 0.30624999999999997, + "f1": 0.29791666666666666, + "accuracy": 0.9769037665905699, + "roc_auc": 0.9798244599199056, + "map": 0.852976977655548, + "precision@recall80": 0.8014614789005033, + "precision@recall90": 0.769246972727664, + "precision@1": 0.875, + "recall@1": 0.6020833333333334, + "f1@1": 0.6674603174603174, + "accuracy@1": 0.9843298401349306, + "precision@3": 0.4861111111111111, + "recall@3": 0.8319444444444445, + "f1@3": 0.558531746031746, + "accuracy@3": 0.9695501298219082, + "precision@5": 0.35000000000000003, + "recall@5": 0.909722222222222, + "f1@5": 0.46231661856661854, + "accuracy@5": 0.9474214507463442, + "precision@8": 0.22916666666666666, + "recall@8": 0.9305555555555555, + "f1@8": 0.3416712916712917, + "accuracy@8": 0.9075311626261447, + "precision@10": 0.18333333333333335, + "recall@10": 0.9305555555555555, + "f1@10": 0.28709138084138086, + "accuracy@10": 0.8788183843391154, + "precision@15": 0.12222222222222223, + "recall@15": 0.9305555555555555, + "f1@15": 0.20560311112749194, + "accuracy@15": 0.8070364386215417, + "precision@20": 0.09166666666666667, + "recall@20": 0.9305555555555555, + "f1@20": 0.16033278315887015, + "accuracy@20": 0.7352544929039676, + "precision@30": 0.06805555555555556, + "recall@30": 0.9722222222222222, + "f1@30": 0.12332609607870516, + "accuracy@30": 0.5956373417852413, + "precision@40": 0.0529490427927928, + "recall@40": 0.9861111111111112, + "f1@40": 0.09809856268685807, + "accuracy@40": 0.4664277795114698, + "precision@50": 0.04461808794069109, + "recall@50": 1.0, + "f1@50": 0.08373590180424924, + "accuracy@50": 0.3595111827187476 + } + } + }, + "nda-17": { + "micro_doc": { + "class_binary": { + "accuracy": 0.5882352941176471, + "precision_entailment": 0.5625, + "recall_entailment": 1.0, + "f1_entailment": 0.72, + "precision_contradiction": 1.0, + "recall_contradiction": 0.125, + "f1_contradiction": 0.2222222222222222, + "precision_mean": 0.78125, + "precision_hmean": 0.72, + "recall_mean": 0.5625, + "recall_hmean": 0.2222222222222222, + "f1_mean": 0.4711111111111111, + "f1_hmean": 0.33962264150943394 + }, + "class": { + "accuracy": 0.7704918032786885, + "precision_entailment": 0.42105263157894735, + "recall_entailment": 0.8888888888888888, + "f1_entailment": 0.5714285714285714, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.21052631578947367, + "precision_hmean": 0.0, + "recall_mean": 0.4444444444444444, + "recall_hmean": 0.0, + "f1_mean": 0.2857142857142857, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.8, + "recall": 0.6956521739130435, + "f1": 0.7441860465116279, + "accuracy": 0.9929396662387676, + "roc_auc": 0.9897464948307605, + "map": 0.826419425892727, + "precision@recall80": 0.59375, + "precision@recall90": 0.2441860465116279, + "precision@1": 0.8235294117647058, + "recall@1": 0.6086956521739131, + "f1@1": 0.7, + "accuracy@1": 0.9922978177150192, + "precision@3": 0.39215686274509803, + "recall@3": 0.8695652173913043, + "f1@3": 0.5405405405405406, + "accuracy@3": 0.9781771501925546, + "precision@5": 0.23529411764705882, + "recall@5": 0.8695652173913043, + "f1@5": 0.3703703703703704, + "accuracy@5": 0.9563543003851092, + "precision@8": 0.15441176470588236, + "recall@8": 0.9130434782608695, + "f1@8": 0.2641509433962264, + "accuracy@8": 0.9249037227214377, + "precision@10": 0.12941176470588237, + "recall@10": 0.9565217391304348, + "f1@10": 0.227979274611399, + "accuracy@10": 0.9043645699614891, + "precision@15": 0.09019607843137255, + "recall@15": 1.0, + "f1@15": 0.1654676258992806, + "accuracy@15": 0.8510911424903723, + "precision@20": 0.06764705882352941, + "recall@20": 1.0, + "f1@20": 0.12672176308539945, + "accuracy@20": 0.7965340179717587, + "precision@30": 0.045098039215686274, + "recall@30": 1.0, + "f1@30": 0.08630393996247654, + "accuracy@30": 0.6874197689345315, + "precision@40": 0.034074074074074076, + "recall@40": 1.0, + "f1@40": 0.0659025787965616, + "accuracy@40": 0.5815147625160462, + "precision@50": 0.027544910179640718, + "recall@50": 1.0, + "f1@50": 0.05361305361305361, + "accuracy@50": 0.47881899871630296 + } + }, + "macro_doc": { + "span": { + "precision": 0.7647058823529411, + "recall": 0.7058823529411765, + "f1": 0.7058823529411764, + "accuracy": 0.9927352317463704, + "roc_auc": 0.9850152571926766, + "map": 0.8339366515837103, + "precision@recall80": 0.7809954751131221, + "precision@recall90": 0.7809954751131221, + "precision@1": 0.8235294117647058, + "recall@1": 0.6470588235294118, + "f1@1": 0.7058823529411764, + "accuracy@1": 0.9924996935263695, + "precision@3": 0.392156862745098, + "recall@3": 0.8823529411764706, + "f1@3": 0.5294117647058824, + "accuracy@3": 0.9717971290305111, + "precision@5": 0.23529411764705888, + "recall@5": 0.8823529411764706, + "f1@5": 0.3641456582633053, + "accuracy@5": 0.9446962785427869, + "precision@8": 0.15441176470588236, + "recall@8": 0.9117647058823529, + "f1@8": 0.2601307189542484, + "accuracy@8": 0.9063979439876712, + "precision@10": 0.12941176470588237, + "recall@10": 0.9411764705882353, + "f1@10": 0.22459893048128346, + "accuracy@10": 0.8810796246942428, + "precision@15": 0.09019607843137255, + "recall@15": 1.0, + "f1@15": 0.16392733564013842, + "accuracy@15": 0.8145403547514638, + "precision@20": 0.06764705882352942, + "recall@20": 1.0, + "f1@20": 0.12579577285459637, + "accuracy@20": 0.7467882285321531, + "precision@30": 0.045098039215686274, + "recall@30": 1.0, + "f1@30": 0.08586337760910814, + "accuracy@30": 0.6112839760935321, + "precision@40": 0.034033613445378155, + "recall@40": 1.0, + "f1@40": 0.06557582382546515, + "accuracy@40": 0.48418308499944895, + "precision@50": 0.02756302521008403, + "recall@50": 1.0, + "f1@50": 0.05348534587288912, + "accuracy@50": 0.36548555524990367 + } + } + }, + "nda-18": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.9344262295081968, + "precision_entailment": 0.8181818181818182, + "recall_entailment": 0.8181818181818182, + "f1_entailment": 0.8181818181818182, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.4090909090909091, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.8333333333333334, + "recall": 0.5, + "f1": 0.625, + "accuracy": 0.9842243645924628, + "roc_auc": 0.9714371437143714, + "map": 0.7151889471610886, + "precision@recall80": 0.5853658536585366, + "precision@recall90": 0.1656441717791411, + "precision@1": 0.8181818181818182, + "recall@1": 0.3, + "f1@1": 0.43902439024390244, + "accuracy@1": 0.9798422436459246, + "precision@3": 0.6060606060606061, + "recall@3": 0.6666666666666666, + "f1@3": 0.6349206349206349, + "accuracy@3": 0.9798422436459246, + "precision@5": 0.45454545454545453, + "recall@5": 0.8333333333333334, + "f1@5": 0.5882352941176471, + "accuracy@5": 0.9693251533742331, + "precision@8": 0.29545454545454547, + "recall@8": 0.8666666666666667, + "f1@8": 0.44067796610169496, + "accuracy@8": 0.9421560035056967, + "precision@10": 0.24545454545454545, + "recall@10": 0.9, + "f1@10": 0.38571428571428573, + "accuracy@10": 0.9246275197195443, + "precision@15": 0.17575757575757575, + "recall@15": 0.9666666666666667, + "f1@15": 0.29743589743589743, + "accuracy@15": 0.8799298860648553, + "precision@20": 0.13636363636363635, + "recall@20": 1.0, + "f1@20": 0.24000000000000002, + "accuracy@20": 0.8334794040315513, + "precision@30": 0.09090909090909091, + "recall@30": 1.0, + "f1@30": 0.16666666666666669, + "accuracy@30": 0.7370727432077125, + "precision@40": 0.06818181818181818, + "recall@40": 1.0, + "f1@40": 0.1276595744680851, + "accuracy@40": 0.6406660823838738, + "precision@50": 0.05639097744360902, + "recall@50": 1.0, + "f1@50": 0.10676156583629892, + "accuracy@50": 0.5600350569675723 + } + }, + "macro_doc": { + "span": { + "precision": 0.7393939393939394, + "recall": 0.5757575757575757, + "f1": 0.5868686868686869, + "accuracy": 0.9831428210989203, + "roc_auc": 0.9730517532113278, + "map": 0.8088885609340154, + "precision@recall80": 0.7212908303817395, + "precision@recall90": 0.7205693296602388, + "precision@1": 0.8181818181818182, + "recall@1": 0.40151515151515144, + "f1@1": 0.503030303030303, + "accuracy@1": 0.9774043030605568, + "precision@3": 0.6060606060606061, + "recall@3": 0.7000000000000001, + "f1@3": 0.6123376623376623, + "accuracy@3": 0.9712005974543636, + "precision@5": 0.45454545454545453, + "recall@5": 0.8772727272727273, + "f1@5": 0.5637806637806638, + "accuracy@5": 0.9583072178090263, + "precision@8": 0.29545454545454547, + "recall@8": 0.9, + "f1@8": 0.42411527866073323, + "accuracy@8": 0.9242369156560512, + "precision@10": 0.24545454545454543, + "recall@10": 0.9181818181818181, + "f1@10": 0.3711651984379257, + "accuracy@10": 0.9025645619285823, + "precision@15": 0.17575757575757575, + "recall@15": 0.9818181818181819, + "f1@15": 0.28867389060887516, + "accuracy@15": 0.8500909946830807, + "precision@20": 0.13636363636363638, + "recall@20": 1.0, + "f1@20": 0.2337354345259484, + "accuracy@20": 0.7931828376371356, + "precision@30": 0.0909090909090909, + "recall@30": 1.0, + "f1@30": 0.1635255808535091, + "accuracy@30": 0.6757301599088819, + "precision@40": 0.06818181818181819, + "recall@40": 1.0, + "f1@40": 0.12577856263722298, + "accuracy@40": 0.5582774821806278, + "precision@50": 0.05574279379157428, + "recall@50": 1.0, + "f1@50": 0.1044249521370315, + "accuracy@50": 0.480736112656365 + } + } + }, + "nda-19": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.819672131147541, + "precision_entailment": 0.9210526315789473, + "recall_entailment": 0.813953488372093, + "f1_entailment": 0.8641975308641974, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.4605263157894737, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.7962962962962963, + "recall": 0.4942528735632184, + "f1": 0.6099290780141844, + "accuracy": 0.9859442882698697, + "roc_auc": 0.9632039704141656, + "map": 0.6661487676183546, + "precision@recall80": 0.36649214659685864, + "precision@recall90": 0.18501170960187355, + "precision@1": 0.8372093023255814, + "recall@1": 0.41379310344827586, + "f1@1": 0.5538461538461538, + "accuracy@1": 0.9851776130845898, + "precision@3": 0.4573643410852713, + "recall@3": 0.6781609195402298, + "f1@3": 0.5462962962962963, + "accuracy@3": 0.9749552772808586, + "precision@5": 0.31627906976744186, + "recall@5": 0.7816091954022989, + "f1@5": 0.4503311258278146, + "accuracy@5": 0.9575773064145158, + "precision@8": 0.2180232558139535, + "recall@8": 0.8620689655172413, + "f1@8": 0.3480278422273782, + "accuracy@8": 0.9281880909787886, + "precision@10": 0.17906976744186046, + "recall@10": 0.8850574712643678, + "f1@10": 0.2978723404255319, + "accuracy@10": 0.9072323025811397, + "precision@15": 0.12403100775193798, + "recall@15": 0.9195402298850575, + "f1@15": 0.2185792349726776, + "accuracy@15": 0.8538205980066446, + "precision@20": 0.0941860465116279, + "recall@20": 0.9310344827586207, + "f1@20": 0.1710665258711721, + "accuracy@20": 0.7993866598517761, + "precision@30": 0.06608969315499606, + "recall@30": 0.9655172413793104, + "f1@30": 0.12371134020618557, + "accuracy@30": 0.6958855098389982, + "precision@40": 0.05149700598802395, + "recall@40": 0.9885057471264368, + "f1@40": 0.09789413773477519, + "accuracy@40": 0.5949399437771531, + "precision@50": 0.042177538008827856, + "recall@50": 0.9885057471264368, + "f1@50": 0.08090310442144873, + "accuracy@50": 0.5006388959877331 + } + }, + "macro_doc": { + "span": { + "precision": 0.6356589147286822, + "recall": 0.555813953488372, + "f1": 0.5674317930131884, + "accuracy": 0.9810358526387007, + "roc_auc": 0.9739440355868184, + "map": 0.8200096606572488, + "precision@recall80": 0.7523378860588164, + "precision@recall90": 0.7212611976523543, + "precision@1": 0.8372093023255814, + "recall@1": 0.5810077519379845, + "f1@1": 0.6466223698781838, + "accuracy@1": 0.9827238842047255, + "precision@3": 0.4573643410852714, + "recall@3": 0.8201550387596899, + "f1@3": 0.5436507936507936, + "accuracy@3": 0.9659008668812347, + "precision@5": 0.3162790697674418, + "recall@5": 0.8906976744186046, + "f1@5": 0.43204134366925084, + "accuracy@5": 0.9403434052761512, + "precision@8": 0.2180232558139535, + "recall@8": 0.9426356589147288, + "f1@8": 0.33155784783691744, + "accuracy@8": 0.8990477366346487, + "precision@10": 0.1790697674418604, + "recall@10": 0.9531007751937984, + "f1@10": 0.28413195331799984, + "accuracy@10": 0.8698611218603152, + "precision@15": 0.12403100775193804, + "recall@15": 0.9713178294573644, + "f1@15": 0.21006226235904393, + "accuracy@15": 0.796915397333661, + "precision@20": 0.09418604651162786, + "recall@20": 0.9751937984496125, + "f1@20": 0.16534700890615947, + "accuracy@20": 0.7216855660421024, + "precision@30": 0.06583610188261353, + "recall@30": 0.9875968992248062, + "f1@30": 0.12000914030391986, + "accuracy@30": 0.5944355911018427, + "precision@40": 0.0518813040615366, + "recall@40": 0.996124031007752, + "f1@40": 0.09629095201163848, + "accuracy@40": 0.4756804373222384, + "precision@50": 0.04317720925215707, + "recall@50": 0.996124031007752, + "f1@50": 0.08100392889882828, + "accuracy@50": 0.37270715674903376 + } + } + }, + "nda-2": { + "micro_doc": { + "class_binary": { + "accuracy": 0.88, + "precision_entailment": 0.0, + "recall_entailment": 0.0, + "f1_entailment": 0.0, + "precision_contradiction": 0.88, + "recall_contradiction": 1.0, + "f1_contradiction": 0.9361702127659575, + "precision_mean": 0.44, + "precision_hmean": 0.0, + "recall_mean": 0.5, + "recall_hmean": 0.0, + "f1_mean": 0.46808510638297873, + "f1_hmean": 0.0 + }, + "class": { + "accuracy": 0.7540983606557377, + "precision_entailment": 0.0, + "recall_entailment": 0.0, + "f1_entailment": 0.0, + "precision_contradiction": 0.925, + "recall_contradiction": 0.8409090909090909, + "f1_contradiction": 0.8809523809523809, + "precision_mean": 0.4625, + "precision_hmean": 0.0, + "recall_mean": 0.42045454545454547, + "recall_hmean": 0.0, + "f1_mean": 0.44047619047619047, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.8688524590163934, + "recall": 0.5247524752475248, + "f1": 0.654320987654321, + "accuracy": 0.9864341085271318, + "roc_auc": 0.9817469703265335, + "map": 0.782102338538608, + "precision@recall80": 0.675, + "precision@recall90": 0.48663101604278075, + "precision@1": 0.86, + "recall@1": 0.42574257425742573, + "f1@1": 0.5695364238410596, + "accuracy@1": 0.9842538759689923, + "precision@3": 0.48, + "recall@3": 0.7128712871287128, + "f1@3": 0.5737051792828685, + "accuracy@3": 0.9740794573643411, + "precision@5": 0.332, + "recall@5": 0.8217821782178217, + "f1@5": 0.472934472934473, + "accuracy@5": 0.9551841085271318, + "precision@8": 0.23, + "recall@8": 0.9108910891089109, + "f1@8": 0.36726546906187624, + "accuracy@8": 0.9232073643410853, + "precision@10": 0.19, + "recall@10": 0.9405940594059405, + "f1@10": 0.3161397670549085, + "accuracy@10": 0.9004360465116279, + "precision@15": 0.132, + "recall@15": 0.9801980198019802, + "f1@15": 0.2326674500587544, + "accuracy@15": 0.841812015503876, + "precision@20": 0.099, + "recall@20": 0.9801980198019802, + "f1@20": 0.1798365122615804, + "accuracy@20": 0.78125, + "precision@30": 0.06852103120759837, + "recall@30": 1.0, + "f1@30": 0.12825396825396826, + "accuracy@30": 0.6673934108527132, + "precision@40": 0.05260416666666667, + "recall@40": 1.0, + "f1@40": 0.09995051954477982, + "accuracy@40": 0.5593507751937985, + "precision@50": 0.04332904332904333, + "recall@50": 1.0, + "f1@50": 0.08305921052631579, + "accuracy@50": 0.45978682170542634 + } + }, + "macro_doc": { + "span": { + "precision": 0.6113333333333333, + "recall": 0.5075, + "f1": 0.5386410256410257, + "accuracy": 0.9831046971679228, + "roc_auc": 0.9788646250471185, + "map": 0.8611117605220866, + "precision@recall80": 0.8156703103659625, + "precision@recall90": 0.8116775253731775, + "precision@1": 0.86, + "recall@1": 0.6075, + "f1@1": 0.6732063492063491, + "accuracy@1": 0.9818829260963731, + "precision@3": 0.47999999999999987, + "recall@3": 0.8308333333333333, + "f1@3": 0.5581818181818183, + "accuracy@3": 0.9639932194270738, + "precision@5": 0.3319999999999999, + "recall@5": 0.8766666666666666, + "f1@5": 0.43989676989676973, + "accuracy@5": 0.9366989251193274, + "precision@8": 0.23, + "recall@8": 0.9541666666666666, + "f1@8": 0.34074675324675296, + "accuracy@8": 0.8931175716531793, + "precision@10": 0.1899999999999999, + "recall@10": 0.9616666666666666, + "f1@10": 0.29287351537351536, + "accuracy@10": 0.8614563431938279, + "precision@15": 0.13199999999999998, + "recall@15": 0.98, + "f1@15": 0.21795619162997004, + "accuracy@15": 0.7822623531731137, + "precision@20": 0.09899999999999994, + "recall@20": 0.98, + "f1@20": 0.17045476262867557, + "accuracy@20": 0.7005757956106516, + "precision@30": 0.06815527950310557, + "recall@30": 1.0, + "f1@30": 0.12292316525313625, + "accuracy@30": 0.5631312268692179, + "precision@40": 0.052183915281741336, + "recall@40": 1.0, + "f1@40": 0.09641505949248629, + "accuracy@40": 0.4424563379207808, + "precision@50": 0.04298309851316666, + "recall@50": 1.0, + "f1@50": 0.08060346211970121, + "accuracy@50": 0.3396049414398538 + } + } + }, + "nda-20": { + "micro_doc": { + "class_binary": { + "accuracy": 0.84, + "precision_entailment": 0.8461538461538461, + "recall_entailment": 0.8461538461538461, + "f1_entailment": 0.8461538461538461, + "precision_contradiction": 0.8333333333333334, + "recall_contradiction": 0.8333333333333334, + "f1_contradiction": 0.8333333333333334, + "precision_mean": 0.8397435897435898, + "precision_hmean": 0.8396946564885496, + "recall_mean": 0.8397435897435898, + "recall_hmean": 0.8396946564885496, + "f1_mean": 0.8397435897435898, + "f1_hmean": 0.8396946564885496 + }, + "class": { + "accuracy": 0.639344262295082, + "precision_entailment": 0.6470588235294118, + "recall_entailment": 0.8461538461538461, + "f1_entailment": 0.7333333333333334, + "precision_contradiction": 0.38461538461538464, + "recall_contradiction": 0.8333333333333334, + "f1_contradiction": 0.5263157894736842, + "precision_mean": 0.5158371040723982, + "precision_hmean": 0.4824561403508773, + "recall_mean": 0.8397435897435898, + "recall_hmean": 0.8396946564885496, + "f1_mean": 0.6298245614035087, + "f1_hmean": 0.6128133704735376 + }, + "span": { + "precision": 0.8478260869565217, + "recall": 0.6190476190476191, + "f1": 0.7155963302752294, + "accuracy": 0.9874188311688312, + "roc_auc": 0.9931047248831505, + "map": 0.8398179392455799, + "precision@recall80": 0.7727272727272727, + "precision@recall90": 0.6477272727272727, + "precision@1": 0.88, + "recall@1": 0.3492063492063492, + "f1@1": 0.5, + "accuracy@1": 0.9821428571428571, + "precision@3": 0.5733333333333334, + "recall@3": 0.6825396825396826, + "f1@3": 0.6231884057971014, + "accuracy@3": 0.9788961038961039, + "precision@5": 0.432, + "recall@5": 0.8571428571428571, + "f1@5": 0.5744680851063829, + "accuracy@5": 0.9675324675324676, + "precision@8": 0.305, + "recall@8": 0.9682539682539683, + "f1@8": 0.4638783269961977, + "accuracy@8": 0.942775974025974, + "precision@10": 0.252, + "recall@10": 1.0, + "f1@10": 0.402555910543131, + "accuracy@10": 0.9241071428571429, + "precision@15": 0.168, + "recall@15": 1.0, + "f1@15": 0.28767123287671237, + "accuracy@15": 0.8733766233766234, + "precision@20": 0.126, + "recall@20": 1.0, + "f1@20": 0.2238010657193606, + "accuracy@20": 0.8226461038961039, + "precision@30": 0.084, + "recall@30": 1.0, + "f1@30": 0.15498154981549817, + "accuracy@30": 0.721185064935065, + "precision@40": 0.063, + "recall@40": 1.0, + "f1@40": 0.11853245531514582, + "accuracy@40": 0.619724025974026, + "precision@50": 0.05088852988691438, + "recall@50": 1.0, + "f1@50": 0.09684857801691006, + "accuracy@50": 0.5231331168831169 + } + }, + "macro_doc": { + "span": { + "precision": 0.8166666666666668, + "recall": 0.6543333333333333, + "f1": 0.6916090576090574, + "accuracy": 0.9847736872594561, + "roc_auc": 0.9911293562401271, + "map": 0.884063888888889, + "precision@recall80": 0.8192222222222222, + "precision@recall90": 0.8181111111111111, + "precision@1": 0.88, + "recall@1": 0.5063333333333333, + "f1@1": 0.5909841269841271, + "accuracy@1": 0.9793829403897992, + "precision@3": 0.5733333333333333, + "recall@3": 0.8043333333333333, + "f1@3": 0.602961038961039, + "accuracy@3": 0.973397925357077, + "precision@5": 0.43200000000000005, + "recall@5": 0.9123333333333333, + "f1@5": 0.532085248085248, + "accuracy@5": 0.9582311417664549, + "precision@8": 0.305, + "recall@8": 0.975, + "f1@8": 0.42724686424686426, + "accuracy@8": 0.9277645205358249, + "precision@10": 0.252, + "recall@10": 1.0, + "f1@10": 0.3733011433011433, + "accuracy@10": 0.9062772870711256, + "precision@15": 0.168, + "recall@15": 1.0, + "f1@15": 0.27118890576825694, + "accuracy@15": 0.8446042315519664, + "precision@20": 0.126, + "recall@20": 1.0, + "f1@20": 0.21325318160100767, + "accuracy@20": 0.7829311760328069, + "precision@30": 0.084, + "recall@30": 1.0, + "f1@30": 0.14960297500694983, + "accuracy@30": 0.6595850649944884, + "precision@40": 0.063, + "recall@40": 1.0, + "f1@40": 0.11528004259859546, + "accuracy@40": 0.5362389539561698, + "precision@50": 0.05080228334198236, + "recall@50": 1.0, + "f1@50": 0.09452880542272885, + "accuracy@50": 0.4242265222120911 + } + } + }, + "nda-3": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.8688524590163934, + "precision_entailment": 0.9512195121951219, + "recall_entailment": 0.8666666666666667, + "f1_entailment": 0.9069767441860465, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.47560975609756095, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.7377049180327869, + "recall": 0.6, + "f1": 0.6617647058823529, + "accuracy": 0.9883603238866396, + "roc_auc": 0.9626996818846187, + "map": 0.7104892187629145, + "precision@recall80": 0.5263157894736842, + "precision@recall90": 0.2518518518518518, + "precision@1": 0.8666666666666667, + "recall@1": 0.52, + "f1@1": 0.65, + "accuracy@1": 0.9893724696356275, + "precision@3": 0.43703703703703706, + "recall@3": 0.7866666666666666, + "f1@3": 0.5619047619047619, + "accuracy@3": 0.9767206477732794, + "precision@5": 0.28444444444444444, + "recall@5": 0.8533333333333334, + "f1@5": 0.4266666666666667, + "accuracy@5": 0.9564777327935222, + "precision@8": 0.18611111111111112, + "recall@8": 0.8933333333333333, + "f1@8": 0.3080459770114943, + "accuracy@8": 0.923836032388664, + "precision@10": 0.14888888888888888, + "recall@10": 0.8933333333333333, + "f1@10": 0.2552380952380952, + "accuracy@10": 0.9010627530364372, + "precision@15": 0.1037037037037037, + "recall@15": 0.9333333333333333, + "f1@15": 0.18666666666666668, + "accuracy@15": 0.8456477732793523, + "precision@20": 0.08, + "recall@20": 0.96, + "f1@20": 0.14769230769230768, + "accuracy@20": 0.7897267206477733, + "precision@30": 0.054436987322893364, + "recall@30": 0.9733333333333334, + "f1@30": 0.10310734463276836, + "accuracy@30": 0.6786437246963563, + "precision@40": 0.042686397268070574, + "recall@40": 1.0, + "f1@40": 0.08187772925764192, + "accuracy@40": 0.5743927125506073, + "precision@50": 0.0350140056022409, + "recall@50": 1.0, + "f1@50": 0.06765899864682003, + "accuracy@50": 0.4769736842105263 + } + }, + "macro_doc": { + "span": { + "precision": 0.6703703703703703, + "recall": 0.6759259259259259, + "f1": 0.6430687830687832, + "accuracy": 0.9857962183959069, + "roc_auc": 0.9808407203226066, + "map": 0.86293325907361, + "precision@recall80": 0.8065577405051089, + "precision@recall90": 0.8069545659019344, + "precision@1": 0.8666666666666667, + "recall@1": 0.6574074074074073, + "f1@1": 0.7155555555555556, + "accuracy@1": 0.9882946045613014, + "precision@3": 0.43703703703703684, + "recall@3": 0.8814814814814815, + "f1@3": 0.5529100529100529, + "accuracy@3": 0.9690072778908956, + "precision@5": 0.2844444444444443, + "recall@5": 0.9092592592592593, + "f1@5": 0.4106701940035273, + "accuracy@5": 0.9421177734703853, + "precision@8": 0.18611111111111112, + "recall@8": 0.95, + "f1@8": 0.2986083052749717, + "accuracy@8": 0.8977572591418261, + "precision@10": 0.1488888888888888, + "recall@10": 0.95, + "f1@10": 0.24833684833684824, + "accuracy@10": 0.867726081579643, + "precision@15": 0.10370370370370373, + "recall@15": 0.9711111111111111, + "f1@15": 0.18214424951267058, + "accuracy@15": 0.7947120941531626, + "precision@20": 0.07999999999999997, + "recall@20": 0.9866666666666666, + "f1@20": 0.14458907919777478, + "accuracy@20": 0.7213815110048937, + "precision@30": 0.054391534391534394, + "recall@30": 0.9911111111111112, + "f1@30": 0.10138729392050073, + "accuracy@30": 0.5814127826348672, + "precision@40": 0.04257150007150006, + "recall@40": 1.0, + "f1@40": 0.0805604161297706, + "accuracy@40": 0.459253121327639, + "precision@50": 0.0350455818335943, + "recall@50": 1.0, + "f1@50": 0.06699270617472476, + "accuracy@50": 0.35363827355594557 + } + } + }, + "nda-4": { + "micro_doc": { + "class_binary": { + "accuracy": 0.9433962264150944, + "precision_entailment": 0.9433962264150944, + "recall_entailment": 1.0, + "f1_entailment": 0.970873786407767, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.4716981132075472, + "precision_hmean": 0.0, + "recall_mean": 0.5, + "recall_hmean": 0.0, + "f1_mean": 0.4854368932038835, + "f1_hmean": 0.0 + }, + "class": { + "accuracy": 0.9016393442622951, + "precision_entailment": 0.9074074074074074, + "recall_entailment": 0.98, + "f1_entailment": 0.9423076923076924, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.4537037037037037, + "precision_hmean": 0.0, + "recall_mean": 0.49, + "recall_hmean": 0.0, + "f1_mean": 0.4711538461538462, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.6781609195402298, + "recall": 0.6555555555555556, + "f1": 0.6666666666666666, + "accuracy": 0.9871739130434782, + "roc_auc": 0.9737053461443705, + "map": 0.7361675011456795, + "precision@recall80": 0.5333333333333333, + "precision@recall90": 0.13322368421052633, + "precision@1": 0.8679245283018868, + "recall@1": 0.5111111111111111, + "f1@1": 0.6433566433566433, + "accuracy@1": 0.9889130434782609, + "precision@3": 0.44654088050314467, + "recall@3": 0.7888888888888889, + "f1@3": 0.570281124497992, + "accuracy@3": 0.9767391304347826, + "precision@5": 0.29056603773584905, + "recall@5": 0.8555555555555555, + "f1@5": 0.43380281690140843, + "accuracy@5": 0.956304347826087, + "precision@8": 0.18867924528301888, + "recall@8": 0.8888888888888888, + "f1@8": 0.31128404669260706, + "accuracy@8": 0.9230434782608695, + "precision@10": 0.15471698113207547, + "recall@10": 0.9111111111111111, + "f1@10": 0.2645161290322581, + "accuracy@10": 0.9008695652173913, + "precision@15": 0.10817610062893082, + "recall@15": 0.9555555555555556, + "f1@15": 0.1943502824858757, + "accuracy@15": 0.845, + "precision@20": 0.0820754716981132, + "recall@20": 0.9666666666666667, + "f1@20": 0.15130434782608693, + "accuracy@20": 0.7878260869565218, + "precision@30": 0.056265984654731455, + "recall@30": 0.9777777777777777, + "f1@30": 0.10640870616686819, + "accuracy@30": 0.678695652173913, + "precision@40": 0.043243243243243246, + "recall@40": 0.9777777777777777, + "f1@40": 0.0828235294117647, + "accuracy@40": 0.576304347826087, + "precision@50": 0.036090835360908353, + "recall@50": 0.9888888888888889, + "f1@50": 0.06964006259780907, + "accuracy@50": 0.4830434782608696 + } + }, + "macro_doc": { + "span": { + "precision": 0.6572327044025157, + "recall": 0.6562893081761005, + "f1": 0.6214135968852951, + "accuracy": 0.9865375730320449, + "roc_auc": 0.9833345972123236, + "map": 0.8459600327732124, + "precision@recall80": 0.776860132848648, + "precision@recall90": 0.7730964002611498, + "precision@1": 0.8679245283018868, + "recall@1": 0.620754716981132, + "f1@1": 0.6911949685534591, + "accuracy@1": 0.9893905225368987, + "precision@3": 0.44654088050314455, + "recall@3": 0.8481132075471697, + "f1@3": 0.5514824797843666, + "accuracy@3": 0.9693087065555651, + "precision@5": 0.2905660377358489, + "recall@5": 0.8889937106918239, + "f1@5": 0.41587301587301595, + "accuracy@5": 0.9394221282257862, + "precision@8": 0.18867924528301888, + "recall@8": 0.9069182389937107, + "f1@8": 0.2993358842415444, + "accuracy@8": 0.8930490014224902, + "precision@10": 0.15471698113207538, + "recall@10": 0.9352201257861635, + "f1@10": 0.2559346314063295, + "accuracy@10": 0.862577746201154, + "precision@15": 0.10817610062893085, + "recall@15": 0.9672955974842767, + "f1@15": 0.18926404060465626, + "accuracy@15": 0.784646207432148, + "precision@20": 0.08207547169811316, + "recall@20": 0.9861635220125786, + "f1@20": 0.14821005081874633, + "accuracy@20": 0.7055854697980942, + "precision@30": 0.056121332864565034, + "recall@30": 0.9899371069182389, + "f1@30": 0.10455891148580272, + "accuracy@30": 0.5706413019042152, + "precision@40": 0.043283343257707475, + "recall@40": 0.9899371069182389, + "f1@40": 0.08196577304486055, + "accuracy@40": 0.45497248086070613, + "precision@50": 0.03645452834693434, + "recall@50": 0.9937106918238994, + "f1@50": 0.06964433500099183, + "accuracy@50": 0.35925248208486005 + } + } + }, + "nda-5": { + "micro_doc": { + "class_binary": { + "accuracy": 0.9642857142857143, + "precision_entailment": 0.9642857142857143, + "recall_entailment": 1.0, + "f1_entailment": 0.9818181818181818, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.48214285714285715, + "precision_hmean": 0.0, + "recall_mean": 0.5, + "recall_hmean": 0.0, + "f1_mean": 0.4909090909090909, + "f1_hmean": 0.0 + }, + "class": { + "accuracy": 0.8852459016393442, + "precision_entailment": 1.0, + "recall_entailment": 0.9074074074074074, + "f1_entailment": 0.9514563106796117, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.5, + "precision_hmean": 0.0, + "recall_mean": 0.4537037037037037, + "recall_hmean": 0.0, + "f1_mean": 0.47572815533980584, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.9295774647887324, + "recall": 0.6470588235294118, + "f1": 0.7630057803468208, + "accuracy": 0.9914814045293996, + "roc_auc": 0.9877903613154028, + "map": 0.8451563712818726, + "precision@recall80": 0.7884615384615384, + "precision@recall90": 0.5287356321839081, + "precision@1": 0.9464285714285714, + "recall@1": 0.5196078431372549, + "f1@1": 0.6708860759493671, + "accuracy@1": 0.9891959276958238, + "precision@3": 0.5059523809523809, + "recall@3": 0.8333333333333334, + "f1@3": 0.6296296296296295, + "accuracy@3": 0.9792229378765842, + "precision@5": 0.3357142857142857, + "recall@5": 0.9215686274509803, + "f1@5": 0.4921465968586387, + "accuracy@5": 0.9596924994805734, + "precision@8": 0.21875, + "recall@8": 0.9607843137254902, + "f1@8": 0.3563636363636363, + "accuracy@8": 0.9264492000831083, + "precision@10": 0.175, + "recall@10": 0.9607843137254902, + "f1@10": 0.29607250755287007, + "accuracy@10": 0.9031788905048826, + "precision@15": 0.11666666666666667, + "recall@15": 0.9607843137254902, + "f1@15": 0.208067940552017, + "accuracy@15": 0.8450031165593185, + "precision@20": 0.0875, + "recall@20": 0.9607843137254902, + "f1@20": 0.160392798690671, + "accuracy@20": 0.7868273426137544, + "precision@30": 0.059844404548174746, + "recall@30": 0.9803921568627451, + "f1@30": 0.11280315848843768, + "accuracy@30": 0.6731768127986703, + "precision@40": 0.045454545454545456, + "recall@40": 0.9803921568627451, + "f1@40": 0.08688097306689835, + "accuracy@40": 0.563266154165801, + "precision@50": 0.03803131991051454, + "recall@50": 1.0, + "f1@50": 0.07327586206896552, + "accuracy@50": 0.46395179721587365 + } + }, + "macro_doc": { + "span": { + "precision": 0.78125, + "recall": 0.6953869047619047, + "f1": 0.7208797155225726, + "accuracy": 0.9915472554174791, + "roc_auc": 0.9950018313274166, + "map": 0.9413989712732921, + "precision@recall80": 0.9015962363206153, + "precision@recall90": 0.8943914522330673, + "precision@1": 0.9464285714285714, + "recall@1": 0.6933035714285716, + "f1@1": 0.7623015873015874, + "accuracy@1": 0.990161999199519, + "precision@3": 0.5059523809523808, + "recall@3": 0.9177083333333333, + "f1@3": 0.6123337971552257, + "accuracy@3": 0.973489661970785, + "precision@5": 0.3357142857142857, + "recall@5": 0.9681547619047618, + "f1@5": 0.4699317547531833, + "accuracy@5": 0.9472317486204261, + "precision@8": 0.21875, + "recall@8": 0.9851190476190476, + "f1@8": 0.3396651959151958, + "accuracy@8": 0.9035075612972558, + "precision@10": 0.175, + "recall@10": 0.9851190476190476, + "f1@10": 0.2837162837162837, + "accuracy@10": 0.8736709481968935, + "precision@15": 0.11666666666666668, + "recall@15": 0.9851190476190476, + "f1@15": 0.201294109367622, + "accuracy@15": 0.7990794154459866, + "precision@20": 0.0875, + "recall@20": 0.9851190476190476, + "f1@20": 0.15612463364792548, + "accuracy@20": 0.7244878826950804, + "precision@30": 0.05977891156462585, + "recall@30": 0.9918154761904762, + "f1@30": 0.11031048763848797, + "accuracy@30": 0.583685011980711, + "precision@40": 0.04532212378194521, + "recall@40": 0.9918154761904762, + "f1@40": 0.08523678740861039, + "accuracy@40": 0.4540195508179303, + "precision@50": 0.03788890323509063, + "recall@50": 1.0, + "f1@50": 0.07200625092738584, + "accuracy@50": 0.3459721181324036 + } + } + }, + "nda-7": { + "micro_doc": { + "class_binary": { + "accuracy": 0.8679245283018868, + "precision_entailment": 0.8809523809523809, + "recall_entailment": 0.9487179487179487, + "f1_entailment": 0.9135802469135802, + "precision_contradiction": 0.8181818181818182, + "recall_contradiction": 0.6428571428571429, + "f1_contradiction": 0.7200000000000001, + "precision_mean": 0.8495670995670996, + "precision_hmean": 0.8484076433121019, + "recall_mean": 0.7957875457875458, + "recall_hmean": 0.766398158803222, + "f1_mean": 0.8167901234567901, + "f1_hmean": 0.8053204353083435 + }, + "class": { + "accuracy": 0.7868852459016393, + "precision_entailment": 0.9473684210526315, + "recall_entailment": 0.9230769230769231, + "f1_entailment": 0.935064935064935, + "precision_contradiction": 0.8571428571428571, + "recall_contradiction": 0.42857142857142855, + "f1_contradiction": 0.5714285714285714, + "precision_mean": 0.9022556390977443, + "precision_hmean": 0.8999999999999999, + "recall_mean": 0.6758241758241759, + "recall_hmean": 0.5853658536585366, + "f1_mean": 0.7532467532467533, + "f1_hmean": 0.70935960591133 + }, + "span": { + "precision": 0.8591549295774648, + "recall": 0.5865384615384616, + "f1": 0.6971428571428572, + "accuracy": 0.9886021505376344, + "roc_auc": 0.9833158482520559, + "map": 0.7799315108490067, + "precision@recall80": 0.5562913907284768, + "precision@recall90": 0.3836734693877551, + "precision@1": 0.8867924528301887, + "recall@1": 0.4519230769230769, + "f1@1": 0.5987261146496815, + "accuracy@1": 0.9864516129032258, + "precision@3": 0.5094339622641509, + "recall@3": 0.7788461538461539, + "f1@3": 0.6159695817490494, + "accuracy@3": 0.9782795698924731, + "precision@5": 0.33962264150943394, + "recall@5": 0.8653846153846154, + "f1@5": 0.48780487804878053, + "accuracy@5": 0.9593548387096774, + "precision@8": 0.2240566037735849, + "recall@8": 0.9134615384615384, + "f1@8": 0.3598484848484849, + "accuracy@8": 0.9273118279569893, + "precision@10": 0.1830188679245283, + "recall@10": 0.9326923076923077, + "f1@10": 0.305993690851735, + "accuracy@10": 0.9053763440860215, + "precision@15": 0.12327044025157233, + "recall@15": 0.9423076923076923, + "f1@15": 0.21802002224694103, + "accuracy@15": 0.8488172043010753, + "precision@20": 0.09339622641509433, + "recall@20": 0.9519230769230769, + "f1@20": 0.17010309278350513, + "accuracy@20": 0.792258064516129, + "precision@30": 0.06451612903225806, + "recall@30": 0.9807692307692307, + "f1@30": 0.12106824925816023, + "accuracy@30": 0.681505376344086, + "precision@40": 0.0495907558979297, + "recall@40": 0.9903846153846154, + "f1@40": 0.09445208619899129, + "accuracy@40": 0.5752688172043011, + "precision@50": 0.04097714736012608, + "recall@50": 1.0, + "f1@50": 0.07872823618470855, + "accuracy@50": 0.47655913978494624 + } + }, + "macro_doc": { + "span": { + "precision": 0.710691823899371, + "recall": 0.6130503144654088, + "f1": 0.6373356203544883, + "accuracy": 0.9874406365576607, + "roc_auc": 0.9847267129272066, + "map": 0.8663056374397636, + "precision@recall80": 0.8050532322476538, + "precision@recall90": 0.7977796733846775, + "precision@1": 0.8867924528301887, + "recall@1": 0.565880503144654, + "f1@1": 0.6576519916142557, + "accuracy@1": 0.985521147573182, + "precision@3": 0.5094339622641508, + "recall@3": 0.8375786163522012, + "f1@3": 0.5998243894470312, + "accuracy@3": 0.9733072192290915, + "precision@5": 0.33962264150943405, + "recall@5": 0.9091194968553459, + "f1@5": 0.47029626557928456, + "accuracy@5": 0.947609941868558, + "precision@8": 0.2240566037735849, + "recall@8": 0.9498427672955974, + "f1@8": 0.34711226928208055, + "accuracy@8": 0.9056047191845327, + "precision@10": 0.18301886792452832, + "recall@10": 0.9616352201257861, + "f1@10": 0.2954127633372917, + "accuracy@10": 0.8766284618940761, + "precision@15": 0.12327044025157237, + "recall@15": 0.971069182389937, + "f1@15": 0.21214242558413918, + "accuracy@15": 0.8033272119500111, + "precision@20": 0.09339622641509436, + "recall@20": 0.9748427672955975, + "f1@20": 0.1661657593158823, + "accuracy@20": 0.7302557636508425, + "precision@30": 0.06442048517520219, + "recall@30": 0.9913522012578616, + "f1@30": 0.11867781065371363, + "accuracy@30": 0.5930439040742206, + "precision@40": 0.049627255287632656, + "recall@40": 0.9976415094339622, + "f1@40": 0.09316172298667015, + "accuracy@40": 0.4687829713389787, + "precision@50": 0.04131309312675914, + "recall@50": 1.0, + "f1@50": 0.0783434407276733, + "accuracy@50": 0.36134297233046037 + } + } + }, + "nda-8": { + "micro_doc": { + "class_binary": { + "accuracy": NaN, + "precision_entailment": NaN, + "recall_entailment": NaN, + "f1_entailment": NaN, + "precision_contradiction": NaN, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": NaN, + "precision_hmean": NaN, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "class": { + "accuracy": 0.9016393442622951, + "precision_entailment": 0.8979591836734694, + "recall_entailment": 0.9777777777777777, + "f1_entailment": 0.9361702127659575, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.4489795918367347, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.9152542372881356, + "recall": 0.6923076923076923, + "f1": 0.7883211678832116, + "accuracy": 0.9932652113330237, + "roc_auc": 0.9970829391359193, + "map": 0.9007606628233995, + "precision@recall80": 0.8513513513513513, + "precision@recall90": 0.6698113207547169, + "precision@1": 0.9555555555555556, + "recall@1": 0.5512820512820513, + "f1@1": 0.6991869918699188, + "accuracy@1": 0.9914073385973061, + "precision@3": 0.5111111111111111, + "recall@3": 0.8846153846153846, + "f1@3": 0.6478873239436619, + "accuracy@3": 0.9825824431026474, + "precision@5": 0.32, + "recall@5": 0.9230769230769231, + "f1@5": 0.4752475247524752, + "accuracy@5": 0.9630747793776127, + "precision@8": 0.20277777777777778, + "recall@8": 0.9358974358974359, + "f1@8": 0.33333333333333337, + "accuracy@8": 0.9321876451463075, + "precision@10": 0.16666666666666666, + "recall@10": 0.9615384615384616, + "f1@10": 0.28409090909090906, + "accuracy@10": 0.9122155132373433, + "precision@15": 0.11555555555555555, + "recall@15": 1.0, + "f1@15": 0.20717131474103584, + "accuracy@15": 0.8613562470970738, + "precision@20": 0.08666666666666667, + "recall@20": 1.0, + "f1@20": 0.15950920245398773, + "accuracy@20": 0.8091035764050163, + "precision@30": 0.05847076461769116, + "recall@30": 1.0, + "f1@30": 0.1104815864022663, + "accuracy@30": 0.7083139804923363, + "precision@40": 0.04421768707482993, + "recall@40": 1.0, + "f1@40": 0.08469055374592835, + "accuracy@40": 0.6084533209475151, + "precision@50": 0.03566529492455418, + "recall@50": 1.0, + "f1@50": 0.06887417218543046, + "accuracy@50": 0.5102183000464469 + } + }, + "macro_doc": { + "span": { + "precision": 0.84, + "recall": 0.757037037037037, + "f1": 0.7792592592592593, + "accuracy": 0.9911369664441516, + "roc_auc": 0.9988693295064321, + "map": 0.9598701298701299, + "precision@recall80": 0.943939393939394, + "precision@recall90": 0.9444444444444443, + "precision@1": 0.9555555555555556, + "recall@1": 0.6837037037037037, + "f1@1": 0.767003367003367, + "accuracy@1": 0.990695696123536, + "precision@3": 0.5111111111111113, + "recall@3": 0.9748148148148148, + "f1@3": 0.6438746438746441, + "accuracy@3": 0.9786567739674279, + "precision@5": 0.32, + "recall@5": 0.9866666666666666, + "f1@5": 0.46211640211640226, + "accuracy@5": 0.9529032987566969, + "precision@8": 0.20277777777777778, + "recall@8": 0.9888888888888889, + "f1@8": 0.32300785634118967, + "accuracy@8": 0.9128218153618134, + "precision@10": 0.16666666666666669, + "recall@10": 0.9933333333333334, + "f1@10": 0.27310541310541314, + "accuracy@10": 0.8864985395812827, + "precision@15": 0.11555555555555563, + "recall@15": 1.0, + "f1@15": 0.19827886710239645, + "accuracy@15": 0.8200937804058674, + "precision@20": 0.08666666666666667, + "recall@20": 1.0, + "f1@20": 0.15377794508229284, + "accuracy@20": 0.7527941666443226, + "precision@30": 0.05863814124683694, + "recall@30": 1.0, + "f1@30": 0.10779381000278614, + "accuracy@30": 0.634482033669198, + "precision@40": 0.04474925235794801, + "recall@40": 1.0, + "f1@40": 0.08378289328177123, + "accuracy@40": 0.5201266524769115, + "precision@50": 0.03651130395626235, + "recall@50": 1.0, + "f1@50": 0.06911355020312707, + "accuracy@50": 0.4091220781506958 + } + } + } + } +} \ No newline at end of file