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": 0.8371335504885994, + "precision_entailment": 0.8715596330275229, + "recall_entailment": 0.8962264150943396, + "f1_entailment": 0.8837209302325582, + "precision_contradiction": 0.7528089887640449, + "recall_contradiction": 0.7052631578947368, + "f1_contradiction": 0.7282608695652174, + "precision_mean": 0.8121843108957839, + "precision_hmean": 0.8078436349790582, + "recall_mean": 0.8007447864945383, + "recall_hmean": 0.7893594592918707, + "f1_mean": 0.8059908998988878, + "f1_hmean": 0.7984945899325703 + }, + "class": { + "accuracy": 0.8582449373191899, + "precision_entailment": 0.8865784499054821, + "recall_entailment": 0.9036608863198459, + "f1_entailment": 0.8950381679389313, + "precision_contradiction": 0.6705882352941176, + "recall_contradiction": 0.6, + "f1_contradiction": 0.6333333333333333, + "precision_mean": 0.7785833425997999, + "precision_hmean": 0.7636036447770573, + "recall_mean": 0.751830443159923, + "recall_hmean": 0.7211686314710405, + "f1_mean": 0.7641857506361323, + "f1_hmean": 0.7417797386164988 + }, + "span": { + "precision": 0.8527968596663396, + "recall": 0.7076547231270358, + "f1": 0.7734757454383623, + "accuracy": 0.990762082796421, + "roc_auc": 0.9835390107638605, + "map": 0.8108232134816151, + "precision@recall80": 0.7407686510926903, + "precision@recall90": 0.43135725429017163, + "precision@1": 0.8957654723127035, + "recall@1": 0.44788273615635177, + "f1@1": 0.5971769815418023, + "accuracy@1": 0.9865333309134467, + "precision@3": 0.5249728555917481, + "recall@3": 0.7874592833876222, + "f1@3": 0.6299674267100978, + "accuracy@3": 0.9793825659267863, + "precision@5": 0.35309446254071664, + "recall@5": 0.8827361563517915, + "f1@5": 0.5044206607724523, + "accuracy@5": 0.9613423111127244, + "precision@8": 0.23350977198697068, + "recall@8": 0.9340390879478827, + "f1@8": 0.3736156351791531, + "accuracy@8": 0.9301983702063559, + "precision@10": 0.18973941368078176, + "recall@10": 0.9486970684039088, + "f1@10": 0.31623235613463624, + "accuracy@10": 0.9085645837492513, + "precision@15": 0.1298588490770901, + "recall@15": 0.9739413680781759, + "f1@15": 0.22916267484192374, + "accuracy@15": 0.8539719414145447, + "precision@20": 0.098371335504886, + "recall@20": 0.9837133550488599, + "f1@20": 0.17885697364524725, + "accuracy@20": 0.7986896313907693, + "precision@30": 0.066659357526587, + "recall@30": 0.990228013029316, + "f1@30": 0.1249101181304571, + "accuracy@30": 0.6907747872012197, + "precision@40": 0.05096763430096764, + "recall@40": 0.995114006514658, + "f1@40": 0.0969687351214093, + "accuracy@40": 0.5869253525472332, + "precision@50": 0.041659570119562624, + "recall@50": 0.995928338762215, + "f1@50": 0.07997384338728133, + "accuracy@50": 0.4893010762445779 + } + }, + "macro_label_micro_doc": { + "class_binary": { + "accuracy": 0.7951142636625242, + "precision_entailment": 0.7758610362383948, + "recall_entailment": 0.8117127755285649, + "f1_entailment": 0.7843417330606812, + "precision_contradiction": 0.4318659281894576, + "recall_contradiction": 0.40799512987012987, + "f1_contradiction": 0.39901535516454867, + "precision_mean": 0.603863482213926, + "precision_hmean": 0.4094965325163345, + "recall_mean": 0.6098539526993474, + "recall_hmean": 0.38706971514511535, + "f1_mean": 0.5916785441126149, + "f1_hmean": 0.39417641693218225 + }, + "class": { + "accuracy": 0.8582449373191899, + "precision_entailment": 0.7938138553485757, + "recall_entailment": 0.8142701713719463, + "f1_entailment": 0.7939066924650364, + "precision_contradiction": 0.1600556438791733, + "recall_contradiction": 0.3470508658008658, + "f1_contradiction": 0.33207729316797946, + "precision_mean": 0.47693474961387444, + "precision_hmean": 0.1277274816971088, + "recall_mean": 0.5271377367758947, + "recall_hmean": 0.2655511741977725, + "f1_mean": 0.5035165207117296, + "f1_hmean": 0.26336732235333243 + }, + "span": { + "precision": 0.866661270551219, + "recall": 0.7011668957413617, + "f1": 0.7623920422804824, + "accuracy": 0.9907150594258518, + "roc_auc": 0.9811808154994585, + "map": 0.8064398460781775, + "precision@recall80": 0.682203351639341, + "precision@recall90": 0.5055485217563462, + "precision@1": 0.8855024740397157, + "recall@1": 0.464014462979984, + "f1@1": 0.6016467865639659, + "accuracy@1": 0.9865244461444358, + "precision@3": 0.512913421821055, + "recall@3": 0.7808011318828871, + "f1@3": 0.6121631148233067, + "accuracy@3": 0.9784478567727468, + "precision@5": 0.3485803980896687, + "recall@5": 0.8774272923983816, + "f1@5": 0.49423281365433513, + "accuracy@5": 0.960543715507883, + "precision@8": 0.2306300743062098, + "recall@8": 0.924729055725392, + "f1@8": 0.36653678587372984, + "accuracy@8": 0.9292051773426895, + "precision@10": 0.1875324242905608, + "recall@10": 0.9399773121221171, + "f1@10": 0.31074806912867453, + "accuracy@10": 0.9074818750263292, + "precision@15": 0.1290574670844345, + "recall@15": 0.9726187196096786, + "f1@15": 0.22680189850849816, + "accuracy@15": 0.8528598875557645, + "precision@20": 0.09819437555127596, + "recall@20": 0.9843652886261239, + "f1@20": 0.17790076582292438, + "accuracy@20": 0.7974528375531502, + "precision@30": 0.06641319179552561, + "recall@30": 0.9902936909851431, + "f1@30": 0.12415742666286737, + "accuracy@30": 0.6892455558615541, + "precision@40": 0.05072863516194803, + "recall@40": 0.9955395436610054, + "f1@40": 0.09635009757615273, + "accuracy@40": 0.5847209655778851, + "precision@50": 0.04145063466855522, + "recall@50": 0.9962156761829796, + "f1@50": 0.07945993566218021, + "accuracy@50": 0.4863669218076402 + } + }, + "macro_label_macro_doc": { + "span": { + "precision": 0.7866913908638111, + "recall": 0.7490492420729963, + "f1": 0.7451650664993013, + "accuracy": 0.9894721892347907, + "roc_auc": 0.9863045363510087, + "map": 0.8930193825574447, + "precision@recall80": 0.8613994822716389, + "precision@recall90": 0.8519820833012657, + "precision@1": 0.8855024740397157, + "recall@1": 0.5969318508970789, + "f1@1": 0.6748454989813111, + "accuracy@1": 0.9852400659269516, + "precision@3": 0.5129134218210551, + "recall@3": 0.8643068866858536, + "f1@3": 0.6001991722245095, + "accuracy@3": 0.9720517079521749, + "precision@5": 0.3485803980896686, + "recall@5": 0.9237101417734799, + "f1@5": 0.47150174729262356, + "accuracy@5": 0.9472886161977944, + "precision@8": 0.2306300743062098, + "recall@8": 0.9484609896091866, + "f1@8": 0.3483404377925399, + "accuracy@8": 0.9056533324971842, + "precision@10": 0.18753242429056075, + "recall@10": 0.958499336150795, + "f1@10": 0.2964738415175402, + "accuracy@10": 0.8772647905464603, + "precision@15": 0.1290574670844345, + "recall@15": 0.9871378407277281, + "f1@15": 0.21821080398422496, + "accuracy@15": 0.8060753693952991, + "precision@20": 0.09819437555127596, + "recall@20": 0.9935933640238952, + "f1@20": 0.17214472694796204, + "accuracy@20": 0.7337900763557997, + "precision@30": 0.06642596998543797, + "recall@30": 0.9963162965520667, + "f1@30": 0.12121195817758616, + "accuracy@30": 0.6019786878013711, + "precision@40": 0.05093242461705958, + "recall@40": 0.9986372522812921, + "f1@40": 0.09486957101776052, + "accuracy@40": 0.48053667552168544, + "precision@50": 0.04186100771990234, + "recall@50": 0.9988652504573068, + "f1@50": 0.07894454614400336, + "accuracy@50": 0.3736079454747932 + } + }, + "micro_label_macro_doc": { + "class": { + "accuracy": 0.8582449373191899, + "precision_entailment": 0.8832718738456441, + "recall_entailment": 0.894135418315746, + "f1_entailment": 0.8809319019631394, + "precision_contradiction": 0.5398907103825137, + "recall_contradiction": 0.5581761006289307, + "f1_contradiction": 0.5466756513926327, + "precision_mean": 0.7115812921140787, + "precision_hmean": 0.5392435039562837, + "recall_mean": 0.7313421903044544, + "recall_hmean": 0.5896367387575989, + "f1_mean": 0.7161273692679871, + "f1_hmean": 0.5902298720190158 + }, + "span": { + "precision": 0.7998487668683107, + "recall": 0.7664566206504321, + "f1": 0.7596770448154825, + "accuracy": 0.9896016273857465, + "roc_auc": 0.9900088103044302, + "map": 0.9034595616159704, + "precision@recall80": 0.8704753343261584, + "precision@recall90": 0.861410792771996, + "precision@1": 0.8957654723127035, + "recall@1": 0.5967956672354062, + "f1@1": 0.6786374682140169, + "accuracy@1": 0.9854201767591975, + "precision@3": 0.5249728555917492, + "recall@3": 0.8819722351481311, + "f1@3": 0.6156257694531325, + "accuracy@3": 0.9731813121032175, + "precision@5": 0.3530944625407153, + "recall@5": 0.9352638177963915, + "f1@5": 0.4791805190828001, + "accuracy@5": 0.9480478432735556, + "precision@8": 0.23350977198697068, + "recall@8": 0.9623991779122074, + "f1@8": 0.3539096931150036, + "accuracy@8": 0.9062379485324887, + "precision@10": 0.18973941368078104, + "recall@10": 0.9722681091980765, + "f1@10": 0.3008670005190841, + "accuracy@10": 0.8776490279153966, + "precision@15": 0.129858849077091, + "recall@15": 0.98971226927253, + "f1@15": 0.21986596742510056, + "accuracy@15": 0.8056728803531421, + "precision@20": 0.09837133550488565, + "recall@20": 0.9932184220050669, + "f1@20": 0.17265175313273612, + "accuracy@20": 0.7327673566704149, + "precision@30": 0.06661929040133303, + "recall@30": 0.996502895403547, + "f1@30": 0.12164884401900827, + "accuracy@30": 0.6001266015734019, + "precision@40": 0.05109098580543829, + "recall@40": 0.9985522982265653, + "f1@40": 0.09521223295555102, + "accuracy@40": 0.4791513982616855, + "precision@50": 0.04202623943738449, + "recall@50": 0.9988237423090844, + "f1@50": 0.07928149746261272, + "accuracy@50": 0.37258693791653463 + } + }, + "label_wise": { + "nda-1": { + "micro_doc": { + "class_binary": { + "accuracy": 0.4827586206896552, + "precision_entailment": 0.6666666666666666, + "recall_entailment": 0.42105263157894735, + "f1_entailment": 0.5161290322580646, + "precision_contradiction": 0.35294117647058826, + "recall_contradiction": 0.6, + "f1_contradiction": 0.4444444444444445, + "precision_mean": 0.5098039215686274, + "precision_hmean": 0.46153846153846156, + "recall_mean": 0.5105263157894737, + "recall_hmean": 0.49484536082474223, + "f1_mean": 0.48028673835125457, + "f1_hmean": 0.47761194029850745 + }, + "class": { + "accuracy": 0.7377049180327869, + "precision_entailment": 0.875, + "recall_entailment": 0.3684210526315789, + "f1_entailment": 0.5185185185185185, + "precision_contradiction": 0.375, + "recall_contradiction": 0.6, + "f1_contradiction": 0.4615384615384615, + "precision_mean": 0.625, + "precision_hmean": 0.525, + "recall_mean": 0.4842105263157894, + "recall_hmean": 0.45652173913043476, + "f1_mean": 0.49002849002849, + "f1_hmean": 0.48837209302325574 + }, + "span": { + "precision": 0.7777777777777778, + "recall": 0.603448275862069, + "f1": 0.6796116504854369, + "accuracy": 0.9879781420765027, + "roc_auc": 0.9850942597179266, + "map": 0.6898455211410477, + "precision@recall80": 0.5875, + "precision@recall90": 0.39849624060150374, + "precision@1": 0.7931034482758621, + "recall@1": 0.39655172413793105, + "f1@1": 0.5287356321839081, + "accuracy@1": 0.985063752276867, + "precision@3": 0.4827586206896552, + "recall@3": 0.7241379310344828, + "f1@3": 0.5793103448275863, + "accuracy@3": 0.9777777777777777, + "precision@5": 0.35172413793103446, + "recall@5": 0.8793103448275862, + "f1@5": 0.5024630541871921, + "accuracy@5": 0.9632058287795993, + "precision@8": 0.23706896551724138, + "recall@8": 0.9482758620689655, + "f1@8": 0.37931034482758624, + "accuracy@8": 0.9344262295081968, + "precision@10": 0.19310344827586207, + "recall@10": 0.9655172413793104, + "f1@10": 0.32183908045977005, + "accuracy@10": 0.9140255009107469, + "precision@15": 0.13333333333333333, + "recall@15": 1.0, + "f1@15": 0.23529411764705882, + "accuracy@15": 0.8626593806921676, + "precision@20": 0.1, + "recall@20": 1.0, + "f1@20": 0.18181818181818182, + "accuracy@20": 0.8098360655737705, + "precision@30": 0.06736353077816493, + "recall@30": 1.0, + "f1@30": 0.1262241566920566, + "accuracy@30": 0.7074681238615664, + "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": 0.6551724137931034, + "recall": 0.671264367816092, + "f1": 0.634413096482062, + "accuracy": 0.9872107780181874, + "roc_auc": 0.989899327447751, + "map": 0.8487000547345375, + "precision@recall80": 0.8386699507389163, + "precision@recall90": 0.8189655172413793, + "precision@1": 0.7931034482758621, + "recall@1": 0.5456896551724137, + "f1@1": 0.6094690749863163, + "accuracy@1": 0.9804477580077875, + "precision@3": 0.4827586206896552, + "recall@3": 0.8382183908045977, + "f1@3": 0.5609270040304523, + "accuracy@3": 0.9709796455807344, + "precision@5": 0.35172413793103446, + "recall@5": 0.9267241379310344, + "f1@5": 0.462635066083342, + "accuracy@5": 0.9494230029856009, + "precision@8": 0.23706896551724138, + "recall@8": 0.9482758620689654, + "f1@8": 0.3464535464535465, + "accuracy@8": 0.9096138407985382, + "precision@10": 0.19310344827586207, + "recall@10": 0.9597701149425287, + "f1@10": 0.2968090338779994, + "accuracy@10": 0.8809896371837168, + "precision@15": 0.13333333333333336, + "recall@15": 1.0, + "f1@15": 0.22082136729070231, + "accuracy@15": 0.8099166208249734, + "precision@20": 0.09999999999999999, + "recall@20": 1.0, + "f1@20": 0.17260430723699086, + "accuracy@20": 0.7371989722368906, + "precision@30": 0.06765188834154354, + "recall@30": 1.0, + "f1@30": 0.12201322958917918, + "accuracy@30": 0.6065420001838769, + "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": 0.8360655737704918, + "precision_entailment": 0.8275862068965517, + "recall_entailment": 0.8275862068965517, + "f1_entailment": 0.8275862068965517, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.41379310344827586, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.8958333333333334, + "recall": 0.6417910447761194, + "f1": 0.7478260869565218, + "accuracy": 0.9888160431932125, + "roc_auc": 0.9844601221918909, + "map": 0.8364974422533853, + "precision@recall80": 0.72, + "precision@recall90": 0.43884892086330934, + "precision@1": 0.9310344827586207, + "recall@1": 0.40298507462686567, + "f1@1": 0.5625, + "accuracy@1": 0.9838025453143078, + "precision@3": 0.5057471264367817, + "recall@3": 0.6567164179104478, + "f1@3": 0.5714285714285715, + "accuracy@3": 0.9745468569224837, + "precision@5": 0.3724137931034483, + "recall@5": 0.8059701492537313, + "f1@5": 0.509433962264151, + "accuracy@5": 0.959892016968762, + "precision@8": 0.27155172413793105, + "recall@8": 0.9402985074626866, + "f1@8": 0.4214046822742475, + "accuracy@8": 0.9332819128422677, + "precision@10": 0.21724137931034482, + "recall@10": 0.9402985074626866, + "f1@10": 0.35294117647058826, + "accuracy@10": 0.9109139992286927, + "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": 0.05721830985915493, + "recall@40": 0.9701492537313433, + "f1@40": 0.10806317539484622, + "accuracy@40": 0.5861935981488623, + "precision@50": 0.04703328509406657, + "recall@50": 0.9701492537313433, + "f1@50": 0.08971704623878536, + "accuracy@50": 0.4913227921326649 + } + }, + "macro_doc": { + "span": { + "precision": 0.7459770114942528, + "recall": 0.681185002736727, + "f1": 0.6908045977011493, + "accuracy": 0.9879647398631258, + "roc_auc": 0.9942615467979002, + "map": 0.9315860203280005, + "precision@recall80": 0.9039244663382594, + "precision@recall90": 0.8799235691432632, + "precision@1": 0.9310344827586207, + "recall@1": 0.6915571975916802, + "f1@1": 0.7386973180076627, + "accuracy@1": 0.9862960999281206, + "precision@3": 0.5057471264367817, + "recall@3": 0.8735221674876847, + "f1@3": 0.5607628004179727, + "accuracy@3": 0.9699398265092435, + "precision@5": 0.37241379310344824, + "recall@5": 0.940216201423098, + "f1@5": 0.4617468738158395, + "accuracy@5": 0.9462773113343654, + "precision@8": 0.27155172413793105, + "recall@8": 0.9835796387520525, + "f1@8": 0.3708241724468905, + "accuracy@8": 0.908220735619699, + "precision@10": 0.2172413793103448, + "recall@10": 0.9835796387520525, + "f1@10": 0.3143958161573193, + "accuracy@10": 0.8789056910907088, + "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": 0.05693760262725779, + "recall@40": 0.9923371647509579, + "f1@40": 0.10274801149568989, + "accuracy@40": 0.4761268571304836, + "precision@50": 0.04666175845282193, + "recall@50": 0.9923371647509579, + "f1@50": 0.08584824524000262, + "accuracy@50": 0.3753650388516279 + } + } + }, + "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": 0.9508196721311475, + "precision_entailment": 0.8571428571428571, + "recall_entailment": 0.75, + "f1_entailment": 0.7999999999999999, + "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": 1.0, + "recall": 0.7777777777777778, + "f1": 0.8750000000000001, + "accuracy": 0.9963636363636363, + "roc_auc": 0.9564592318751284, + "map": 0.7972176156255759, + "precision@recall80": 0.11940298507462686, + "precision@recall90": 0.05555555555555555, + "precision@1": 0.75, + "recall@1": 0.6666666666666666, + "f1@1": 0.7058823529411765, + "accuracy@1": 0.990909090909091, + "precision@3": 0.2916666666666667, + "recall@3": 0.7777777777777778, + "f1@3": 0.42424242424242425, + "accuracy@3": 0.9654545454545455, + "precision@5": 0.2, + "recall@5": 0.8888888888888888, + "f1@5": 0.326530612244898, + "accuracy@5": 0.94, + "precision@8": 0.125, + "recall@8": 0.8888888888888888, + "f1@8": 0.2191780821917808, + "accuracy@8": 0.8963636363636364, + "precision@10": 0.1, + "recall@10": 0.8888888888888888, + "f1@10": 0.17977528089887643, + "accuracy@10": 0.8672727272727273, + "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": 0.75, + "f1": 0.75, + "accuracy": 0.9954508196721312, + "roc_auc": 0.9656887755102042, + "map": 0.7916666666666667, + "precision@recall80": 0.7916666666666667, + "precision@recall90": 0.7916666666666667, + "precision@1": 0.75, + "recall@1": 0.6875, + "f1@1": 0.7083333333333333, + "accuracy@1": 0.9896129795504478, + "precision@3": 0.29166666666666663, + "recall@3": 0.75, + "f1@3": 0.4125, + "accuracy@3": 0.95456491238052, + "precision@5": 0.19999999999999998, + "recall@5": 0.875, + "f1@5": 0.3214285714285715, + "accuracy@5": 0.9210378862787008, + "precision@8": 0.125, + "recall@8": 0.875, + "f1@8": 0.21666666666666667, + "accuracy@8": 0.8645998061423656, + "precision@10": 0.09999999999999999, + "recall@10": 0.875, + "f1@10": 0.17803030303030307, + "accuracy@10": 0.8269744193848085, + "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": 0.9508196721311475, + "precision_entailment": 0.9302325581395349, + "recall_entailment": 1.0, + "f1_entailment": 0.963855421686747, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.46511627906976744, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.9655172413793104, + "recall": 0.8316831683168316, + "f1": 0.8936170212765958, + "accuracy": 0.9944873208379272, + "roc_auc": 0.9959997417377122, + "map": 0.9429184178079245, + "precision@recall80": 0.9642857142857143, + "precision@recall90": 0.875, + "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": 0.309375, + "recall@8": 0.9801980198019802, + "f1@8": 0.47030878859857483, + "accuracy@8": 0.9385336273428887, + "precision@10": 0.2525, + "recall@10": 1.0, + "f1@10": 0.4031936127744511, + "accuracy@10": 0.9175854465270121, + "precision@15": 0.16833333333333333, + "recall@15": 1.0, + "f1@15": 0.2881597717546362, + "accuracy@15": 0.8624586549062845, + "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": 0.9729166666666668, + "recall": 0.8752976190476192, + "f1": 0.9096428571428572, + "accuracy": 0.9935614778987725, + "roc_auc": 0.9967666678119883, + "map": 0.9593020124716555, + "precision@recall80": 0.9082142857142858, + "precision@recall90": 0.9089087301587302, + "precision@1": 1.0, + "recall@1": 0.43898809523809523, + "f1@1": 0.6017261904761906, + "accuracy@1": 0.9796903712569248, + "precision@3": 0.7083333333333335, + "recall@3": 0.9023809523809525, + "f1@3": 0.7754761904761909, + "accuracy@3": 0.9823918750230524, + "precision@5": 0.4700000000000001, + "recall@5": 0.9559523809523809, + "f1@5": 0.6132034632034635, + "accuracy@5": 0.9588522843285663, + "precision@8": 0.309375, + "recall@8": 0.9880952380952379, + "f1@8": 0.4587012987012987, + "accuracy@8": 0.9198190807038138, + "precision@10": 0.2525, + "recall@10": 1.0, + "f1@10": 0.39309281404869656, + "accuracy@10": 0.8924984315695441, + "precision@15": 0.16833333333333345, + "recall@15": 1.0, + "f1@15": 0.28236198785734373, + "accuracy@15": 0.8214922109175822, + "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": 0.9836065573770492, + "precision_entailment": 0.9791666666666666, + "recall_entailment": 1.0, + "f1_entailment": 0.9894736842105264, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.4895833333333333, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.9423076923076923, + "recall": 0.8099173553719008, + "f1": 0.8711111111111111, + "accuracy": 0.9932385171368617, + "roc_auc": 0.9930243809584238, + "map": 0.9040177493181316, + "precision@recall80": 0.941747572815534, + "precision@recall90": 0.689873417721519, + "precision@1": 0.9361702127659575, + "recall@1": 0.36363636363636365, + "f1@1": 0.5238095238095237, + "accuracy@1": 0.9813476334809978, + "precision@3": 0.6879432624113475, + "recall@3": 0.8016528925619835, + "f1@3": 0.7404580152671756, + "accuracy@3": 0.9841454884588482, + "precision@5": 0.4765957446808511, + "recall@5": 0.9256198347107438, + "f1@5": 0.6292134831460674, + "accuracy@5": 0.9692235952436465, + "precision@8": 0.3058510638297872, + "recall@8": 0.9504132231404959, + "f1@8": 0.4627766599597586, + "accuracy@8": 0.9377477267428305, + "precision@10": 0.24680851063829787, + "recall@10": 0.9586776859504132, + "f1@10": 0.3925549915397631, + "accuracy@10": 0.9162975052459781, + "precision@15": 0.1673758865248227, + "recall@15": 0.9752066115702479, + "f1@15": 0.2857142857142857, + "accuracy@15": 0.8624387969223595, + "precision@20": 0.1276595744680851, + "recall@20": 0.9917355371900827, + "f1@20": 0.22620169651272384, + "accuracy@20": 0.808580088598741, + "precision@30": 0.08565310492505353, + "recall@30": 0.9917355371900827, + "f1@30": 0.1576872536136662, + "accuracy@30": 0.7010958265329914, + "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": 0.948581560283688, + "recall": 0.8804204660587638, + "f1": 0.9018006815879155, + "accuracy": 0.9916620050734425, + "roc_auc": 0.9955824236298983, + "map": 0.9452358442385038, + "precision@recall80": 0.9249408983451537, + "precision@recall90": 0.9034493874919405, + "precision@1": 0.9361702127659575, + "recall@1": 0.4177558257345492, + "f1@1": 0.5686085781830464, + "accuracy@1": 0.9775334540111313, + "precision@3": 0.6879432624113478, + "recall@3": 0.8827001013171226, + "f1@3": 0.7515750207239571, + "accuracy@3": 0.9799409845469172, + "precision@5": 0.476595744680851, + "recall@5": 0.9701621073961499, + "f1@5": 0.6177615528679363, + "accuracy@5": 0.9616312925794405, + "precision@8": 0.3058510638297872, + "recall@8": 0.9827760891590679, + "f1@8": 0.4520026073217562, + "accuracy@8": 0.921402700652951, + "precision@10": 0.24680851063829784, + "recall@10": 0.986322188449848, + "f1@10": 0.3833519769064201, + "accuracy@10": 0.8939635425250512, + "precision@15": 0.16737588652482283, + "recall@15": 0.9920212765957447, + "f1@15": 0.2791901059916283, + "accuracy@15": 0.82568753069565, + "precision@20": 0.12765957446808507, + "recall@20": 0.9973404255319149, + "f1@20": 0.22120268123968395, + "accuracy@20": 0.7572019285201079, + "precision@30": 0.08601823708206695, + "recall@30": 0.9973404255319149, + "f1@30": 0.15561080877924297, + "accuracy@30": 0.6276471375428836, + "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": 0.9016393442622951, + "precision_entailment": 0.9024390243902439, + "recall_entailment": 0.9487179487179487, + "f1_entailment": 0.9249999999999999, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.45121951219512196, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.7875, + "recall": 0.9264705882352942, + "f1": 0.8513513513513514, + "accuracy": 0.9938598939436226, + "roc_auc": 0.9914525981089448, + "map": 0.7594540469342608, + "precision@recall80": 0.8333333333333334, + "precision@recall90": 0.8051948051948052, + "precision@1": 0.8461538461538461, + "recall@1": 0.4852941176470588, + "f1@1": 0.616822429906542, + "accuracy@1": 0.9885570750767513, + "precision@3": 0.5299145299145299, + "recall@3": 0.9117647058823529, + "f1@3": 0.6702702702702703, + "accuracy@3": 0.9829751604800446, + "precision@5": 0.3384615384615385, + "recall@5": 0.9705882352941176, + "f1@5": 0.5019011406844106, + "accuracy@5": 0.9634384593915714, + "precision@8": 0.21474358974358973, + "recall@8": 0.9852941176470589, + "f1@8": 0.3526315789473684, + "accuracy@8": 0.931342450460508, + "precision@10": 0.1717948717948718, + "recall@10": 0.9852941176470589, + "f1@10": 0.2925764192139738, + "accuracy@10": 0.9095729835333519, + "precision@15": 0.11452991452991453, + "recall@15": 0.9852941176470589, + "f1@15": 0.20520673813169985, + "accuracy@15": 0.8551493162154619, + "precision@20": 0.0858974358974359, + "recall@20": 0.9852941176470589, + "f1@20": 0.15801886792452832, + "accuracy@20": 0.8007256488975719, + "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": 0.80006105006105, + "recall": 0.9188034188034186, + "f1": 0.8307692307692309, + "accuracy": 0.9930242089124051, + "roc_auc": 0.9966306411749662, + "map": 0.9056267806267806, + "precision@recall80": 0.8985042735042736, + "precision@recall90": 0.8985042735042736, + "precision@1": 0.8461538461538461, + "recall@1": 0.564957264957265, + "f1@1": 0.6495726495726496, + "accuracy@1": 0.9870742191492899, + "precision@3": 0.5299145299145298, + "recall@3": 0.9384615384615385, + "f1@3": 0.6474358974358977, + "accuracy@3": 0.9776108566883667, + "precision@5": 0.3384615384615385, + "recall@5": 0.9829059829059827, + "f1@5": 0.48260073260073266, + "accuracy@5": 0.950251990723697, + "precision@8": 0.21474358974358973, + "recall@8": 0.9914529914529914, + "f1@8": 0.34140218755603374, + "accuracy@8": 0.9062344147589538, + "precision@10": 0.17179487179487182, + "recall@10": 0.9914529914529914, + "f1@10": 0.2844420536728229, + "accuracy@10": 0.876724998566811, + "precision@15": 0.11452991452991455, + "recall@15": 0.9914529914529914, + "f1@15": 0.2008965979554215, + "accuracy@15": 0.8029514580864534, + "precision@20": 0.08589743589743591, + "recall@20": 0.9914529914529914, + "f1@20": 0.15535768579246834, + "accuracy@20": 0.7291779176060961, + "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": 0.8032786885245902, + "precision_entailment": 0.6896551724137931, + "recall_entailment": 0.9090909090909091, + "f1_entailment": 0.7843137254901961, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.3448275862068966, + "precision_hmean": 0.0, + "recall_mean": 0.45454545454545453, + "recall_hmean": 0.0, + "f1_mean": 0.39215686274509803, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.9090909090909091, + "recall": 0.5882352941176471, + "f1": 0.7142857142857143, + "accuracy": 0.9890210430009149, + "roc_auc": 0.9805391008862562, + "map": 0.760492245088762, + "precision@recall80": 0.5466666666666666, + "precision@recall90": 0.3026315789473684, + "precision@1": 0.9583333333333334, + "recall@1": 0.45098039215686275, + "f1@1": 0.6133333333333333, + "accuracy@1": 0.9867337602927722, + "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": 0.234375, + "recall@8": 0.8823529411764706, + "f1@8": 0.37037037037037035, + "accuracy@8": 0.9300091491308325, + "precision@10": 0.2, + "recall@10": 0.9411764705882353, + "f1@10": 0.32989690721649484, + "accuracy@10": 0.9107959743824336, + "precision@15": 0.1388888888888889, + "recall@15": 0.9803921568627451, + "f1@15": 0.24330900243309, + "accuracy@15": 0.8577310155535224, + "precision@20": 0.10416666666666667, + "recall@20": 0.9803921568627451, + "f1@20": 0.18832391713747648, + "accuracy@20": 0.8028362305580969, + "precision@30": 0.07083333333333333, + "recall@30": 1.0, + "f1@30": 0.13229571984435798, + "accuracy@30": 0.6939615736505031, + "precision@40": 0.05374077976817703, + "recall@40": 1.0, + "f1@40": 0.10200000000000001, + "accuracy@40": 0.5892040256175664, + "precision@50": 0.04407951598962835, + "recall@50": 1.0, + "f1@50": 0.08443708609271523, + "accuracy@50": 0.4940530649588289 + } + }, + "macro_doc": { + "span": { + "precision": 0.7986111111111112, + "recall": 0.7243055555555555, + "f1": 0.7374158249158249, + "accuracy": 0.9855088134918102, + "roc_auc": 0.98611622391524, + "map": 0.9203472222222223, + "precision@recall80": 0.8717592592592592, + "precision@recall90": 0.8394675925925924, + "precision@1": 0.9583333333333334, + "recall@1": 0.6854166666666668, + "f1@1": 0.7507936507936508, + "accuracy@1": 0.9860222799974734, + "precision@3": 0.4861111111111111, + "recall@3": 0.8340277777777777, + "f1@3": 0.5600198412698413, + "accuracy@3": 0.9686365851755817, + "precision@5": 0.3500000000000001, + "recall@5": 0.9083333333333333, + "f1@5": 0.46291185666185664, + "accuracy@5": 0.9456209738311084, + "precision@8": 0.234375, + "recall@8": 0.9319444444444445, + "f1@8": 0.34732397232397233, + "accuracy@8": 0.9048995686896321, + "precision@10": 0.20000000000000004, + "recall@10": 0.9694444444444446, + "f1@10": 0.31016830391830386, + "accuracy@10": 0.879992360373196, + "precision@15": 0.1388888888888889, + "recall@15": 0.9916666666666667, + "f1@15": 0.23152903705341785, + "accuracy@15": 0.811701106144984, + "precision@20": 0.10416666666666669, + "recall@20": 0.9916666666666667, + "f1@20": 0.18091249330379766, + "accuracy@20": 0.7399191604274099, + "precision@30": 0.07083333333333335, + "recall@30": 1.0, + "f1@30": 0.1283766011292102, + "accuracy@30": 0.5967559100179034, + "precision@40": 0.05399070945945947, + "recall@40": 1.0, + "f1@40": 0.1000365471829821, + "accuracy@40": 0.4669870636278009, + "precision@50": 0.04461808794069109, + "recall@50": 1.0, + "f1@50": 0.08373590180424924, + "accuracy@50": 0.3595111827187476 + } + } + }, + "nda-17": { + "micro_doc": { + "class_binary": { + "accuracy": 0.7058823529411765, + "precision_entailment": 0.7, + "recall_entailment": 0.7777777777777778, + "f1_entailment": 0.7368421052631577, + "precision_contradiction": 0.7142857142857143, + "recall_contradiction": 0.625, + "f1_contradiction": 0.6666666666666666, + "precision_mean": 0.7071428571428571, + "precision_hmean": 0.7070707070707072, + "recall_mean": 0.7013888888888888, + "recall_hmean": 0.6930693069306931, + "f1_mean": 0.7017543859649122, + "f1_hmean": 0.6999999999999998 + }, + "class": { + "accuracy": 0.7868852459016393, + "precision_entailment": 0.5, + "recall_entailment": 0.7777777777777778, + "f1_entailment": 0.6086956521739131, + "precision_contradiction": 0.4444444444444444, + "recall_contradiction": 0.5, + "f1_contradiction": 0.47058823529411764, + "precision_mean": 0.4722222222222222, + "precision_hmean": 0.47058823529411764, + "recall_mean": 0.6388888888888888, + "recall_hmean": 0.6086956521739131, + "f1_mean": 0.5396419437340154, + "f1_hmean": 0.5308056872037915 + }, + "span": { + "precision": 0.84, + "recall": 0.9130434782608695, + "f1": 0.8749999999999999, + "accuracy": 0.9961489088575096, + "roc_auc": 0.9875371760373884, + "map": 0.8903460964702218, + "precision@recall80": 0.8636363636363636, + "precision@recall90": 0.84, + "precision@1": 0.9411764705882353, + "recall@1": 0.6956521739130435, + "f1@1": 0.7999999999999999, + "accuracy@1": 0.9948652118100129, + "precision@3": 0.4117647058823529, + "recall@3": 0.9130434782608695, + "f1@3": 0.5675675675675675, + "accuracy@3": 0.9794608472400513, + "precision@5": 0.24705882352941178, + "recall@5": 0.9130434782608695, + "f1@5": 0.3888888888888889, + "accuracy@5": 0.9576379974326059, + "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": 0.892156862745098, + "recall": 0.9117647058823529, + "f1": 0.8901960784313725, + "accuracy": 0.9963660474102407, + "roc_auc": 0.9881008855154965, + "map": 0.9222222222222222, + "precision@recall80": 0.8993464052287581, + "precision@recall90": 0.8993464052287581, + "precision@1": 0.9411764705882353, + "recall@1": 0.7647058823529411, + "f1@1": 0.8235294117647056, + "accuracy@1": 0.9945408355579356, + "precision@3": 0.4117647058823529, + "recall@3": 0.9117647058823529, + "f1@3": 0.5529411764705883, + "accuracy@3": 0.9740943661071599, + "precision@5": 0.24705882352941178, + "recall@5": 0.9117647058823529, + "f1@5": 0.38095238095238093, + "accuracy@5": 0.9469935156194358, + "precision@8": 0.15441176470588236, + "recall@8": 0.9117647058823529, + "f1@8": 0.2601307189542484, + "accuracy@8": 0.9063422398878493, + "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": 0.9180327868852459, + "precision_entailment": 0.75, + "recall_entailment": 0.8181818181818182, + "f1_entailment": 0.7826086956521738, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.375, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.9375, + "recall": 0.5, + "f1": 0.6521739130434783, + "accuracy": 0.985977212971078, + "roc_auc": 0.9412841284128413, + "map": 0.7395245171581143, + "precision@recall80": 0.36923076923076925, + "precision@recall90": 0.09060402684563758, + "precision@1": 0.8181818181818182, + "recall@1": 0.3, + "f1@1": 0.43902439024390244, + "accuracy@1": 0.9798422436459246, + "precision@3": 0.5757575757575758, + "recall@3": 0.6333333333333333, + "f1@3": 0.6031746031746033, + "accuracy@3": 0.9780893952673094, + "precision@5": 0.41818181818181815, + "recall@5": 0.7666666666666667, + "f1@5": 0.5411764705882354, + "accuracy@5": 0.9658194566170026, + "precision@8": 0.2727272727272727, + "recall@8": 0.8, + "f1@8": 0.4067796610169491, + "accuracy@8": 0.9386503067484663, + "precision@10": 0.21818181818181817, + "recall@10": 0.8, + "f1@10": 0.34285714285714286, + "accuracy@10": 0.9193689745836985, + "precision@15": 0.15757575757575756, + "recall@15": 0.8666666666666667, + "f1@15": 0.26666666666666666, + "accuracy@15": 0.8746713409290097, + "precision@20": 0.1318181818181818, + "recall@20": 0.9666666666666667, + "f1@20": 0.23199999999999998, + "accuracy@20": 0.8317265556529361, + "precision@30": 0.08787878787878788, + "recall@30": 0.9666666666666667, + "f1@30": 0.16111111111111112, + "accuracy@30": 0.7353198948290973, + "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": 0.7045454545454546, + "recall": 0.5681818181818182, + "f1": 0.6067099567099568, + "accuracy": 0.9847279702630298, + "roc_auc": 0.936431093169615, + "map": 0.783377936211457, + "precision@recall80": 0.713032581453634, + "precision@recall90": 0.7086248679550115, + "precision@1": 0.8181818181818182, + "recall@1": 0.40151515151515144, + "f1@1": 0.503030303030303, + "accuracy@1": 0.9774043030605568, + "precision@3": 0.5757575757575757, + "recall@3": 0.6818181818181818, + "f1@3": 0.5896103896103896, + "accuracy@3": 0.9694708329659782, + "precision@5": 0.41818181818181815, + "recall@5": 0.7681818181818181, + "f1@5": 0.5152958152958153, + "accuracy@5": 0.9519660288606043, + "precision@8": 0.2727272727272727, + "recall@8": 0.7909090909090909, + "f1@8": 0.38992724447269905, + "accuracy@8": 0.9179841440374261, + "precision@10": 0.21818181818181817, + "recall@10": 0.7909090909090909, + "f1@10": 0.3303938485756668, + "accuracy@10": 0.8944936084917751, + "precision@15": 0.15757575757575756, + "recall@15": 0.9, + "f1@15": 0.2597968852612816, + "accuracy@15": 0.8420200412462737, + "precision@20": 0.13181818181818183, + "recall@20": 0.9818181818181819, + "f1@20": 0.22646270725322112, + "accuracy@20": 0.7913646558189538, + "precision@30": 0.08787878787878788, + "recall@30": 0.9818181818181819, + "f1@30": 0.1583307756587039, + "accuracy@30": 0.6739119780907, + "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": 0.8688524590163934, + "precision_entailment": 0.9069767441860465, + "recall_entailment": 0.9069767441860465, + "f1_entailment": 0.9069767441860465, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.45348837209302323, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.9074074074074074, + "recall": 0.5632183908045977, + "f1": 0.6950354609929078, + "accuracy": 0.989010989010989, + "roc_auc": 0.954692935811237, + "map": 0.7265721406294394, + "precision@recall80": 0.32710280373831774, + "precision@recall90": 0.14234234234234233, + "precision@1": 0.8604651162790697, + "recall@1": 0.42528735632183906, + "f1@1": 0.5692307692307692, + "accuracy@1": 0.9856887298747764, + "precision@3": 0.49612403100775193, + "recall@3": 0.735632183908046, + "f1@3": 0.5925925925925927, + "accuracy@3": 0.9775108612317914, + "precision@5": 0.31627906976744186, + "recall@5": 0.7816091954022989, + "f1@5": 0.4503311258278146, + "accuracy@5": 0.9575773064145158, + "precision@8": 0.21511627906976744, + "recall@8": 0.8505747126436781, + "f1@8": 0.34338747099767974, + "accuracy@8": 0.9276769741886021, + "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": 0.09534883720930233, + "recall@20": 0.9425287356321839, + "f1@20": 0.17317845828933476, + "accuracy@20": 0.7998977766419627, + "precision@30": 0.06530291109362707, + "recall@30": 0.9540229885057471, + "f1@30": 0.12223858615611194, + "accuracy@30": 0.6953743930488117, + "precision@40": 0.04970059880239521, + "recall@40": 0.9540229885057471, + "f1@40": 0.09447922595332955, + "accuracy@40": 0.5934065934065934, + "precision@50": 0.04119666503187837, + "recall@50": 0.9655172413793104, + "f1@50": 0.07902163687676388, + "accuracy@50": 0.4996166624073601 + } + }, + "macro_doc": { + "span": { + "precision": 0.7655038759689922, + "recall": 0.6620155038759691, + "f1": 0.6875968992248063, + "accuracy": 0.9861338259550582, + "roc_auc": 0.9750973931770547, + "map": 0.8461187897798405, + "precision@recall80": 0.7844021819254018, + "precision@recall90": 0.7753291497477545, + "precision@1": 0.8604651162790697, + "recall@1": 0.5848837209302326, + "f1@1": 0.6532668881506091, + "accuracy@1": 0.9839029759928043, + "precision@3": 0.496124031007752, + "recall@3": 0.8546511627906979, + "f1@3": 0.5789774824658546, + "accuracy@3": 0.9684984814444048, + "precision@5": 0.31627906976744175, + "recall@5": 0.877906976744186, + "f1@5": 0.4314658210007049, + "accuracy@5": 0.9401651975451595, + "precision@8": 0.21511627906976744, + "recall@8": 0.9302325581395349, + "f1@8": 0.32733571338222484, + "accuracy@8": 0.8977888227688724, + "precision@10": 0.1790697674418604, + "recall@10": 0.9511627906976744, + "f1@10": 0.28424908424908424, + "accuracy@10": 0.8706229113411074, + "precision@15": 0.12403100775193804, + "recall@15": 0.9713178294573643, + "f1@15": 0.21006226235904393, + "accuracy@15": 0.7968346398909697, + "precision@20": 0.09534883720930228, + "recall@20": 0.9798449612403101, + "f1@20": 0.16720747402243855, + "accuracy@20": 0.7231390544141955, + "precision@30": 0.06506090808416393, + "recall@30": 0.9844961240310078, + "f1@30": 0.11875406463023952, + "accuracy@30": 0.5952647623208219, + "precision@40": 0.050137118015024976, + "recall@40": 0.9844961240310078, + "f1@40": 0.09325758497422694, + "accuracy@40": 0.47474396159256776, + "precision@50": 0.042246976694017536, + "recall@50": 0.988372093023256, + "f1@50": 0.07934279933072198, + "accuracy@50": 0.37208283959592003 + } + } + }, + "nda-2": { + "micro_doc": { + "class_binary": { + "accuracy": 0.88, + "precision_entailment": 0.5, + "recall_entailment": 0.5, + "f1_entailment": 0.5, + "precision_contradiction": 0.9318181818181818, + "recall_contradiction": 0.9318181818181818, + "f1_contradiction": 0.9318181818181818, + "precision_mean": 0.7159090909090908, + "precision_hmean": 0.6507936507936508, + "recall_mean": 0.7159090909090908, + "recall_hmean": 0.6507936507936508, + "f1_mean": 0.7159090909090908, + "f1_hmean": 0.6507936507936508 + }, + "class": { + "accuracy": 0.7377049180327869, + "precision_entailment": 0.0, + "recall_entailment": 0.0, + "f1_entailment": 0.0, + "precision_contradiction": 0.9459459459459459, + "recall_contradiction": 0.7954545454545454, + "f1_contradiction": 0.8641975308641975, + "precision_mean": 0.47297297297297297, + "precision_hmean": 0.0, + "recall_mean": 0.3977272727272727, + "recall_hmean": 0.0, + "f1_mean": 0.43209876543209874, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.8873239436619719, + "recall": 0.6237623762376238, + "f1": 0.7325581395348837, + "accuracy": 0.9888565891472868, + "roc_auc": 0.9881812616324955, + "map": 0.8394391139859907, + "precision@recall80": 0.7168141592920354, + "precision@recall90": 0.6275862068965518, + "precision@1": 0.9, + "recall@1": 0.44554455445544555, + "f1@1": 0.5960264900662252, + "accuracy@1": 0.9852228682170543, + "precision@3": 0.49333333333333335, + "recall@3": 0.7326732673267327, + "f1@3": 0.5896414342629482, + "accuracy@3": 0.9750484496124031, + "precision@5": 0.348, + "recall@5": 0.8613861386138614, + "f1@5": 0.49572649572649574, + "accuracy@5": 0.9571220930232558, + "precision@8": 0.24, + "recall@8": 0.9504950495049505, + "f1@8": 0.3832335329341317, + "accuracy@8": 0.9251453488372093, + "precision@10": 0.196, + "recall@10": 0.9702970297029703, + "f1@10": 0.3261231281198004, + "accuracy@10": 0.9018895348837209, + "precision@15": 0.13466666666666666, + "recall@15": 1.0, + "f1@15": 0.23736780258519385, + "accuracy@15": 0.842781007751938, + "precision@20": 0.101, + "recall@20": 1.0, + "f1@20": 0.1834695731153497, + "accuracy@20": 0.782218992248062, + "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": 0.6986666666666665, + "recall": 0.6275, + "f1": 0.6418095238095239, + "accuracy": 0.9863657091720772, + "roc_auc": 0.9933953556952169, + "map": 0.9114934579309579, + "precision@recall80": 0.887624098124098, + "precision@recall90": 0.8784529914529915, + "precision@1": 0.9, + "recall@1": 0.6433333333333334, + "f1@1": 0.7076507936507936, + "accuracy@1": 0.9847816076632323, + "precision@3": 0.49333333333333307, + "recall@3": 0.8533333333333333, + "f1@3": 0.5721356421356423, + "accuracy@3": 0.967129527455223, + "precision@5": 0.3479999999999998, + "recall@5": 0.94, + "f1@5": 0.4635331335331333, + "accuracy@5": 0.940581509322564, + "precision@8": 0.24, + "recall@8": 0.9791666666666667, + "f1@8": 0.35374675324675303, + "accuracy@8": 0.8955360742965339, + "precision@10": 0.1959999999999999, + "recall@10": 0.9916666666666667, + "f1@10": 0.3028735153735153, + "accuracy@10": 0.8637161939515917, + "precision@15": 0.13466666666666663, + "recall@15": 1.0, + "f1@15": 0.2226620739829112, + "accuracy@15": 0.7835325144634362, + "precision@20": 0.10099999999999994, + "recall@20": 1.0, + "f1@20": 0.1740911262650392, + "accuracy@20": 0.7018459569009744, + "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": 0.6, + "precision_entailment": 0.5714285714285714, + "recall_entailment": 0.9230769230769231, + "f1_entailment": 0.7058823529411765, + "precision_contradiction": 0.75, + "recall_contradiction": 0.25, + "f1_contradiction": 0.375, + "precision_mean": 0.6607142857142857, + "precision_hmean": 0.6486486486486487, + "recall_mean": 0.5865384615384616, + "recall_hmean": 0.3934426229508197, + "f1_mean": 0.5404411764705883, + "f1_hmean": 0.489795918367347 + }, + "class": { + "accuracy": 0.6557377049180327, + "precision_entailment": 0.5882352941176471, + "recall_entailment": 0.7692307692307693, + "f1_entailment": 0.6666666666666667, + "precision_contradiction": 0.4, + "recall_contradiction": 0.16666666666666666, + "f1_contradiction": 0.23529411764705882, + "precision_mean": 0.49411764705882355, + "precision_hmean": 0.47619047619047616, + "recall_mean": 0.46794871794871795, + "recall_hmean": 0.273972602739726, + "f1_mean": 0.4509803921568628, + "f1_hmean": 0.34782608695652173 + }, + "span": { + "precision": 0.8695652173913043, + "recall": 0.31746031746031744, + "f1": 0.46511627906976744, + "accuracy": 0.9813311688311688, + "roc_auc": 0.9914453633737266, + "map": 0.8108025423906248, + "precision@recall80": 0.7285714285714285, + "precision@recall90": 0.7215189873417721, + "precision@1": 0.84, + "recall@1": 0.3333333333333333, + "f1@1": 0.47727272727272724, + "accuracy@1": 0.9813311688311688, + "precision@3": 0.5866666666666667, + "recall@3": 0.6984126984126984, + "f1@3": 0.6376811594202899, + "accuracy@3": 0.9797077922077922, + "precision@5": 0.44, + "recall@5": 0.873015873015873, + "f1@5": 0.5851063829787234, + "accuracy@5": 0.9683441558441559, + "precision@8": 0.305, + "recall@8": 0.9682539682539683, + "f1@8": 0.4638783269961977, + "accuracy@8": 0.942775974025974, + "precision@10": 0.248, + "recall@10": 0.9841269841269841, + "f1@10": 0.39616613418530355, + "accuracy@10": 0.9232954545454546, + "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": 0.54, + "recall": 0.37566666666666665, + "f1": 0.41448484848484846, + "accuracy": 0.9780899137738777, + "roc_auc": 0.989728266060823, + "map": 0.8842380952380954, + "precision@recall80": 0.8725714285714287, + "precision@recall90": 0.8531269841269843, + "precision@1": 0.84, + "recall@1": 0.49633333333333335, + "f1@1": 0.574984126984127, + "accuracy@1": 0.9786421996490584, + "precision@3": 0.5866666666666667, + "recall@3": 0.8256666666666668, + "f1@3": 0.6194372294372295, + "accuracy@3": 0.9744592758093644, + "precision@5": 0.44, + "recall@5": 0.9303333333333333, + "f1@5": 0.5426249306249307, + "accuracy@5": 0.9594225459365824, + "precision@8": 0.305, + "recall@8": 0.975, + "f1@8": 0.42724686424686426, + "accuracy@8": 0.9277645205358249, + "precision@10": 0.248, + "recall@10": 0.98, + "f1@10": 0.36663447663447657, + "accuracy@10": 0.9043260675589306, + "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": 0.9180327868852459, + "precision_entailment": 0.9545454545454546, + "recall_entailment": 0.9333333333333333, + "f1_entailment": 0.9438202247191012, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.4772727272727273, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.8181818181818182, + "recall": 0.72, + "f1": 0.7659574468085107, + "accuracy": 0.9916497975708503, + "roc_auc": 0.9654956581549308, + "map": 0.7745932926798709, + "precision@recall80": 0.75, + "precision@recall90": 0.40963855421686746, + "precision@1": 0.8444444444444444, + "recall@1": 0.5066666666666667, + "f1@1": 0.6333333333333333, + "accuracy@1": 0.9888663967611336, + "precision@3": 0.45925925925925926, + "recall@3": 0.8266666666666667, + "f1@3": 0.5904761904761905, + "accuracy@3": 0.9782388663967612, + "precision@5": 0.30666666666666664, + "recall@5": 0.92, + "f1@5": 0.4600000000000001, + "accuracy@5": 0.9590080971659919, + "precision@8": 0.19444444444444445, + "recall@8": 0.9333333333333333, + "f1@8": 0.32183908045977017, + "accuracy@8": 0.9253542510121457, + "precision@10": 0.15555555555555556, + "recall@10": 0.9333333333333333, + "f1@10": 0.26666666666666666, + "accuracy@10": 0.902580971659919, + "precision@15": 0.10666666666666667, + "recall@15": 0.96, + "f1@15": 0.192, + "accuracy@15": 0.84665991902834, + "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": 0.7922222222222222, + "recall": 0.8055555555555556, + "f1": 0.7773015873015873, + "accuracy": 0.9902411567965074, + "roc_auc": 0.9867881421888243, + "map": 0.8899206904206904, + "precision@recall80": 0.8614478114478115, + "precision@recall90": 0.8617571317571319, + "precision@1": 0.8444444444444444, + "recall@1": 0.6574074074074073, + "f1@1": 0.7081481481481482, + "accuracy@1": 0.9879993878278439, + "precision@3": 0.459259259259259, + "recall@3": 0.914814814814815, + "f1@3": 0.5767195767195769, + "accuracy@3": 0.9694509530264693, + "precision@5": 0.3066666666666665, + "recall@5": 0.9600000000000001, + "f1@5": 0.43936507936507924, + "accuracy@5": 0.9441511360859435, + "precision@8": 0.19444444444444445, + "recall@8": 0.9711111111111111, + "f1@8": 0.31017525684192326, + "accuracy@8": 0.8998212156208042, + "precision@10": 0.15555555555555547, + "recall@10": 0.9711111111111111, + "f1@10": 0.2581781181781181, + "accuracy@10": 0.8697900380586211, + "precision@15": 0.10666666666666669, + "recall@15": 0.9866666666666666, + "f1@15": 0.18698085081986016, + "accuracy@15": 0.7964594549103522, + "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": 0.7472527472527473, + "recall": 0.7555555555555555, + "f1": 0.7513812154696132, + "accuracy": 0.9902173913043478, + "roc_auc": 0.9851268785415127, + "map": 0.735147243005955, + "precision@recall80": 0.72, + "precision@recall90": 0.41116751269035534, + "precision@1": 0.8490566037735849, + "recall@1": 0.5, + "f1@1": 0.6293706293706294, + "accuracy@1": 0.9884782608695653, + "precision@3": 0.44654088050314467, + "recall@3": 0.7888888888888889, + "f1@3": 0.570281124497992, + "accuracy@3": 0.9767391304347826, + "precision@5": 0.2943396226415094, + "recall@5": 0.8666666666666667, + "f1@5": 0.43943661971830983, + "accuracy@5": 0.9567391304347826, + "precision@8": 0.1957547169811321, + "recall@8": 0.9222222222222223, + "f1@8": 0.3229571984435798, + "accuracy@8": 0.9243478260869565, + "precision@10": 0.16037735849056603, + "recall@10": 0.9444444444444444, + "f1@10": 0.2741935483870967, + "accuracy@10": 0.9021739130434783, + "precision@15": 0.10943396226415095, + "recall@15": 0.9666666666666667, + "f1@15": 0.19661016949152543, + "accuracy@15": 0.8454347826086956, + "precision@20": 0.0820754716981132, + "recall@20": 0.9666666666666667, + "f1@20": 0.15130434782608693, + "accuracy@20": 0.7878260869565218, + "precision@30": 0.05690537084398977, + "recall@30": 0.9888888888888889, + "f1@30": 0.10761789600967353, + "accuracy@30": 0.6791304347826087, + "precision@40": 0.044226044226044224, + "recall@40": 1.0, + "f1@40": 0.08470588235294117, + "accuracy@40": 0.5771739130434783, + "precision@50": 0.0364963503649635, + "recall@50": 1.0, + "f1@50": 0.0704225352112676, + "accuracy@50": 0.4834782608695652 + } + }, + "macro_doc": { + "span": { + "precision": 0.785624438454627, + "recall": 0.7867924528301887, + "f1": 0.7618149146451033, + "accuracy": 0.9901803514238835, + "roc_auc": 0.9890397021234887, + "map": 0.8641635307510389, + "precision@recall80": 0.8267763899514062, + "precision@recall90": 0.8176275199534796, + "precision@1": 0.8490566037735849, + "recall@1": 0.6238993710691824, + "f1@1": 0.6880503144654089, + "accuracy@1": 0.9890875341207027, + "precision@3": 0.44654088050314467, + "recall@3": 0.8720125786163523, + "f1@3": 0.5602875112309076, + "accuracy@3": 0.9701025489531812, + "precision@5": 0.29433962264150926, + "recall@5": 0.9110062893081761, + "f1@5": 0.42283617849655586, + "accuracy@5": 0.9406952460786343, + "precision@8": 0.1957547169811321, + "recall@8": 0.9364779874213836, + "f1@8": 0.30967732477166415, + "accuracy@8": 0.8946752365519965, + "precision@10": 0.16037735849056595, + "recall@10": 0.9616352201257861, + "f1@10": 0.2643966096796285, + "accuracy@10": 0.8634684214376508, + "precision@15": 0.10943396226415097, + "recall@15": 0.9805031446540879, + "f1@15": 0.19128956779666514, + "accuracy@15": 0.7850849963746668, + "precision@20": 0.08207547169811316, + "recall@20": 0.9805031446540879, + "f1@20": 0.14800421891480123, + "accuracy@20": 0.7057622042332753, + "precision@30": 0.05675026368217509, + "recall@30": 0.9962264150943396, + "f1@30": 0.10570242206327556, + "accuracy@30": 0.5708227242554489, + "precision@40": 0.04422673948412256, + "recall@40": 1.0, + "f1@40": 0.08368192535337793, + "accuracy@40": 0.45559269215445847, + "precision@50": 0.03683188683750038, + "recall@50": 1.0, + "f1@50": 0.07035633215300321, + "accuracy@50": 0.3594339044360937 + } + } + }, + "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": 0.9344262295081968, + "precision_entailment": 0.9636363636363636, + "recall_entailment": 0.9814814814814815, + "f1_entailment": 0.9724770642201834, + "precision_contradiction": 0.0, + "recall_contradiction": 0.0, + "f1_contradiction": 0.0, + "precision_mean": 0.4818181818181818, + "precision_hmean": 0.0, + "recall_mean": 0.49074074074074076, + "recall_hmean": 0.0, + "f1_mean": 0.4862385321100917, + "f1_hmean": 0.0 + }, + "span": { + "precision": 0.8522727272727273, + "recall": 0.7352941176470589, + "f1": 0.7894736842105263, + "accuracy": 0.9916891751506337, + "roc_auc": 0.9909286151310449, + "map": 0.8137353818690921, + "precision@recall80": 0.8282828282828283, + "precision@recall90": 0.5287356321839081, + "precision@1": 0.9464285714285714, + "recall@1": 0.5196078431372549, + "f1@1": 0.6708860759493671, + "accuracy@1": 0.9891959276958238, + "precision@3": 0.5119047619047619, + "recall@3": 0.8431372549019608, + "f1@3": 0.637037037037037, + "accuracy@3": 0.9796384791190526, + "precision@5": 0.32142857142857145, + "recall@5": 0.8823529411764706, + "f1@5": 0.4712041884816754, + "accuracy@5": 0.9580303345107002, + "precision@8": 0.21651785714285715, + "recall@8": 0.9509803921568627, + "f1@8": 0.3527272727272727, + "accuracy@8": 0.9260336588406399, + "precision@10": 0.1732142857142857, + "recall@10": 0.9509803921568627, + "f1@10": 0.2930513595166163, + "accuracy@10": 0.9027633492624143, + "precision@15": 0.11666666666666667, + "recall@15": 0.9607843137254902, + "f1@15": 0.208067940552017, + "accuracy@15": 0.8450031165593185, + "precision@20": 0.08928571428571429, + "recall@20": 0.9803921568627451, + "f1@20": 0.1636661211129296, + "accuracy@20": 0.787658425098691, + "precision@30": 0.06044284859365649, + "recall@30": 0.9901960784313726, + "f1@30": 0.11393119007332204, + "accuracy@30": 0.6735923540411386, + "precision@40": 0.046363636363636364, + "recall@40": 1.0, + "f1@40": 0.08861859252823631, + "accuracy@40": 0.5640972366507376, + "precision@50": 0.03803131991051454, + "recall@50": 1.0, + "f1@50": 0.07327586206896552, + "accuracy@50": 0.46395179721587365 + } + }, + "macro_doc": { + "span": { + "precision": 0.8300595238095239, + "recall": 0.7883928571428571, + "f1": 0.7791666666666667, + "accuracy": 0.9910016665545266, + "roc_auc": 0.994233579450271, + "map": 0.9284456936912294, + "precision@recall80": 0.8805351394637109, + "precision@recall90": 0.8718645045430761, + "precision@1": 0.9464285714285714, + "recall@1": 0.6754464285714288, + "f1@1": 0.7503968253968253, + "accuracy@1": 0.9899613688269087, + "precision@3": 0.5119047619047618, + "recall@3": 0.9117559523809523, + "f1@3": 0.6153099876314162, + "accuracy@3": 0.9737376778438008, + "precision@5": 0.3214285714285713, + "recall@5": 0.9296130952380952, + "f1@5": 0.4496206174777602, + "accuracy@5": 0.9450264940405096, + "precision@8": 0.21651785714285715, + "recall@8": 0.9800595238095237, + "f1@8": 0.3366473803973803, + "accuracy@8": 0.9030153451800398, + "precision@10": 0.17321428571428568, + "recall@10": 0.9800595238095237, + "f1@10": 0.28113909899624184, + "accuracy@10": 0.8731787320796774, + "precision@15": 0.11666666666666668, + "recall@15": 0.9860119047619047, + "f1@15": 0.201388094330028, + "accuracy@15": 0.7991824374240085, + "precision@20": 0.08928571428571427, + "recall@20": 0.9918154761904762, + "f1@20": 0.15888823909010236, + "accuracy@20": 0.7252150162580348, + "precision@30": 0.06037414965986394, + "recall@30": 0.994047619047619, + "f1@30": 0.11125033726254814, + "accuracy@30": 0.583862694994215, + "precision@40": 0.046214980924802355, + "recall@40": 1.0, + "f1@40": 0.08681139981171117, + "accuracy@40": 0.45436893712813753, + "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": 0.9444444444444444, + "recall_entailment": 0.8717948717948718, + "f1_entailment": 0.9066666666666667, + "precision_contradiction": 0.7058823529411765, + "recall_contradiction": 0.8571428571428571, + "f1_contradiction": 0.7741935483870968, + "precision_mean": 0.8251633986928104, + "precision_hmean": 0.8079207920792079, + "recall_mean": 0.8644688644688645, + "recall_hmean": 0.8644067796610171, + "f1_mean": 0.8404301075268817, + "f1_hmean": 0.8352098259979529 + }, + "class": { + "accuracy": 0.7704918032786885, + "precision_entailment": 0.9444444444444444, + "recall_entailment": 0.8717948717948718, + "f1_entailment": 0.9066666666666667, + "precision_contradiction": 0.5555555555555556, + "recall_contradiction": 0.7142857142857143, + "f1_contradiction": 0.6250000000000001, + "precision_mean": 0.75, + "precision_hmean": 0.6995884773662553, + "recall_mean": 0.7930402930402931, + "recall_hmean": 0.7852193995381063, + "f1_mean": 0.7658333333333334, + "f1_hmean": 0.7399347116430905 + }, + "span": { + "precision": 0.7604166666666666, + "recall": 0.7019230769230769, + "f1": 0.73, + "accuracy": 0.9883870967741936, + "roc_auc": 0.9914908287928524, + "map": 0.8292101312005682, + "precision@recall80": 0.7058823529411765, + "precision@recall90": 0.4017094017094017, + "precision@1": 0.9056603773584906, + "recall@1": 0.46153846153846156, + "f1@1": 0.6114649681528663, + "accuracy@1": 0.9868817204301076, + "precision@3": 0.5345911949685535, + "recall@3": 0.8173076923076923, + "f1@3": 0.6463878326996199, + "accuracy@3": 0.98, + "precision@5": 0.35471698113207545, + "recall@5": 0.9038461538461539, + "f1@5": 0.5094850948509484, + "accuracy@5": 0.9610752688172043, + "precision@8": 0.22877358490566038, + "recall@8": 0.9326923076923077, + "f1@8": 0.36742424242424243, + "accuracy@8": 0.9281720430107527, + "precision@10": 0.18679245283018867, + "recall@10": 0.9519230769230769, + "f1@10": 0.3123028391167192, + "accuracy@10": 0.906236559139785, + "precision@15": 0.12955974842767295, + "recall@15": 0.9903846153846154, + "f1@15": 0.22914349276974416, + "accuracy@15": 0.8509677419354839, + "precision@20": 0.09716981132075472, + "recall@20": 0.9903846153846154, + "f1@20": 0.17697594501718214, + "accuracy@20": 0.7939784946236559, + "precision@30": 0.06578115117014548, + "recall@30": 1.0, + "f1@30": 0.12344213649851633, + "accuracy@30": 0.6823655913978495, + "precision@40": 0.05007221954742417, + "recall@40": 1.0, + "f1@40": 0.09536909674461257, + "accuracy@40": 0.5756989247311828, + "precision@50": 0.04097714736012608, + "recall@50": 1.0, + "f1@50": 0.07872823618470855, + "accuracy@50": 0.47655913978494624 + } + }, + "macro_doc": { + "span": { + "precision": 0.7940251572327043, + "recall": 0.736320754716981, + "f1": 0.7378740756099246, + "accuracy": 0.9875941668523456, + "roc_auc": 0.9918461552038329, + "map": 0.8947588924004017, + "precision@recall80": 0.8463012878107218, + "precision@recall90": 0.8419579023352609, + "precision@1": 0.9056603773584906, + "recall@1": 0.5847484276729559, + "f1@1": 0.6765199161425578, + "accuracy@1": 0.9860718107181848, + "precision@3": 0.5345911949685535, + "recall@3": 0.8784591194968553, + "f1@3": 0.6293841378747042, + "accuracy@3": 0.9752179700069936, + "precision@5": 0.35471698113207556, + "recall@5": 0.9334905660377358, + "f1@5": 0.4880238210426891, + "accuracy@5": 0.9491782767626474, + "precision@8": 0.22877358490566038, + "recall@8": 0.9665094339622642, + "f1@8": 0.35455828238847115, + "accuracy@8": 0.9061368914148181, + "precision@10": 0.18679245283018872, + "recall@10": 0.9797169811320754, + "f1@10": 0.3020591567761379, + "accuracy@10": 0.8774445916949989, + "precision@15": 0.129559748427673, + "recall@15": 0.9976415094339622, + "f1@15": 0.22197219633071477, + "accuracy@15": 0.8057685122933109, + "precision@20": 0.09716981132075474, + "recall@20": 0.9976415094339622, + "f1@20": 0.17244175021041294, + "accuracy@20": 0.7322253658809346, + "precision@30": 0.06567834681042231, + "recall@30": 1.0, + "f1@30": 0.1208143698905708, + "accuracy@30": 0.5934130669680244, + "precision@40": 0.050098953400840196, + "recall@40": 1.0, + "f1@40": 0.09394788650868273, + "accuracy@40": 0.4689707118815489, + "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": 0.9344262295081968, + "precision_entailment": 0.9183673469387755, + "recall_entailment": 1.0, + "f1_entailment": 0.9574468085106383, + "precision_contradiction": 0.0, + "recall_contradiction": NaN, + "f1_contradiction": NaN, + "precision_mean": 0.45918367346938777, + "precision_hmean": 0.0, + "recall_mean": NaN, + "recall_hmean": NaN, + "f1_mean": NaN, + "f1_hmean": NaN + }, + "span": { + "precision": 0.8352941176470589, + "recall": 0.9102564102564102, + "f1": 0.8711656441717791, + "accuracy": 0.9951230840687413, + "roc_auc": 0.9968615821264828, + "map": 0.8596638857700519, + "precision@recall80": 0.875, + "precision@recall90": 0.8554216867469879, + "precision@1": 0.9333333333333333, + "recall@1": 0.5384615384615384, + "f1@1": 0.6829268292682926, + "accuracy@1": 0.9909428704133767, + "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": 0.2, + "recall@8": 0.9230769230769231, + "f1@8": 0.32876712328767127, + "accuracy@8": 0.931723176962378, + "precision@10": 0.16, + "recall@10": 0.9230769230769231, + "f1@10": 0.27272727272727276, + "accuracy@10": 0.910822108685555, + "precision@15": 0.11259259259259259, + "recall@15": 0.9743589743589743, + "f1@15": 0.20185922974767595, + "accuracy@15": 0.8604273107292151, + "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": 0.8996296296296294, + "recall": 0.9703703703703704, + "f1": 0.9160052910052908, + "accuracy": 0.9959435658600193, + "roc_auc": 0.9975709390945775, + "map": 0.9541255935422602, + "precision@recall80": 0.9340740740740741, + "precision@recall90": 0.934722222222222, + "precision@1": 0.9333333333333333, + "recall@1": 0.6837037037037037, + "f1@1": 0.7595959595959597, + "accuracy@1": 0.9900119354397752, + "precision@3": 0.5111111111111113, + "recall@3": 0.9696296296296297, + "f1@3": 0.6398860398860401, + "accuracy@3": 0.978652715669985, + "precision@5": 0.32000000000000006, + "recall@5": 0.9814814814814814, + "f1@5": 0.45952380952380967, + "accuracy@5": 0.9526317830489396, + "precision@8": 0.2, + "recall@8": 0.9814814814814814, + "f1@8": 0.31896745230078566, + "accuracy@8": 0.9122520147920129, + "precision@10": 0.16000000000000003, + "recall@10": 0.9814814814814814, + "f1@10": 0.26524216524216526, + "accuracy@10": 0.8853321692873956, + "precision@15": 0.11259259259259266, + "recall@15": 0.9955555555555555, + "f1@15": 0.19472331154684094, + "accuracy@15": 0.819497210681781, + "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