From f5abaadc54c9725a80919901b489f17bcb2939ba Mon Sep 17 00:00:00 2001 From: Riksin Date: Thu, 18 Dec 2025 07:30:52 -0600 Subject: [PATCH 1/2] Upload robustness score details --- src/data/flip_labels/flip_labels_CARROT.json | 1682 +++++++++++++++++ src/data/flip_labels/flip_labels_kmeans.json | 1682 +++++++++++++++++ src/data/flip_labels/flip_labels_knn.json | 1682 +++++++++++++++++ src/data/flip_labels/flip_labels_mirt.json | 1682 +++++++++++++++++ src/data/flip_labels/flip_labels_mlp.json | 1682 +++++++++++++++++ src/data/flip_labels/flip_labels_nirt.json | 1682 +++++++++++++++++ .../flip_labels/flip_labels_routerDC.json | 1682 +++++++++++++++++ 7 files changed, 11774 insertions(+) create mode 100644 src/data/flip_labels/flip_labels_CARROT.json create mode 100644 src/data/flip_labels/flip_labels_kmeans.json create mode 100644 src/data/flip_labels/flip_labels_knn.json create mode 100644 src/data/flip_labels/flip_labels_mirt.json create mode 100644 src/data/flip_labels/flip_labels_mlp.json create mode 100644 src/data/flip_labels/flip_labels_nirt.json create mode 100644 src/data/flip_labels/flip_labels_routerDC.json diff --git a/src/data/flip_labels/flip_labels_CARROT.json b/src/data/flip_labels/flip_labels_CARROT.json new file mode 100644 index 0000000..2fbe639 --- /dev/null +++ b/src/data/flip_labels/flip_labels_CARROT.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 0 + }, + { + "global index": "AIME_58", + "flip": 1 + }, + { + "global index": "ArcMMLU_12", + "flip": 0 + }, + { + "global index": "ArcMMLU_123", + "flip": 0 + }, + { + "global index": "ArcMMLU_16", + "flip": 1 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 0 + }, + { + "global index": "ArcMMLU_293", + "flip": 0 + }, + { + "global index": "ArcMMLU_349", + "flip": 0 + }, + { + "global index": "ArcMMLU_378", + "flip": 0 + }, + { + "global index": "ArcMMLU_443", + "flip": 0 + }, + { + "global index": "ArcMMLU_496", + "flip": 0 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 0 + }, + { + "global index": "ArcMMLU_676", + "flip": 0 + }, + { + "global index": "ArcMMLU_685", + "flip": 1 + }, + { + "global index": "ArcMMLU_689", + "flip": 0 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 0 + }, + { + "global index": "ArcMMLU_98", + "flip": 1 + }, + { + "global index": "AsDiv_1165", + "flip": 0 + }, + { + "global index": "AsDiv_1347", + "flip": 1 + }, + { + "global index": "AsDiv_472", + "flip": 0 + }, + { + "global index": "AsDiv_733", + "flip": 0 + }, + { + "global index": "ChessInstruct_0", + "flip": 0 + }, + { + "global index": "ChessInstruct_107", + "flip": 0 + }, + { + "global index": "ChessInstruct_144", + "flip": 1 + }, + { + "global index": "ChessInstruct_42", + "flip": 1 + }, + { + "global index": "ChessInstruct_58", + "flip": 0 + }, + { + "global index": "ChessInstruct_71", + "flip": 0 + }, + { + "global index": "ChessInstruct_84", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 0 + }, + { + "global index": "Ethics_deontology_0", + "flip": 0 + }, + { + "global index": "Ethics_deontology_2", + "flip": 0 + }, + { + "global index": "Ethics_deontology_31", + "flip": 0 + }, + { + "global index": "Ethics_deontology_32", + "flip": 0 + }, + { + "global index": "Ethics_deontology_56", + "flip": 0 + }, + { + "global index": "Ethics_justice_1", + "flip": 0 + }, + { + "global index": "Ethics_justice_45", + "flip": 0 + }, + { + "global index": "Ethics_justice_76", + "flip": 0 + }, + { + "global index": "Ethics_justice_84", + "flip": 0 + }, + { + "global index": "Ethics_virtue_14", + "flip": 0 + }, + { + "global index": "Ethics_virtue_26", + "flip": 0 + }, + { + "global index": "Ethics_virtue_30", + "flip": 0 + }, + { + "global index": "Ethics_virtue_48", + "flip": 0 + }, + { + "global index": "Ethics_virtue_51", + "flip": 0 + }, + { + "global index": "FinQA_149", + "flip": 0 + }, + { + "global index": "FinQA_208", + "flip": 0 + }, + { + "global index": "FinQA_56", + "flip": 0 + }, + { + "global index": "FinQA_60", + "flip": 0 + }, + { + "global index": "GSM8K_43", + "flip": 0 + }, + { + "global index": "GeoBench_1002", + "flip": 0 + }, + { + "global index": "GeoBench_1094", + "flip": 0 + }, + { + "global index": "GeoBench_1102", + "flip": 0 + }, + { + "global index": "GeoBench_1113", + "flip": 0 + }, + { + "global index": "GeoBench_124", + "flip": 0 + }, + { + "global index": "GeoBench_1243", + "flip": 0 + }, + { + "global index": "GeoBench_30", + "flip": 0 + }, + { + "global index": "GeoBench_502", + "flip": 0 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 0 + }, + { + "global index": "GeoBench_766", + "flip": 1 + }, + { + "global index": "GeoBench_87", + "flip": 1 + }, + { + "global index": "GeoBench_915", + "flip": 0 + }, + { + "global index": "GeoBench_944", + "flip": 0 + }, + { + "global index": "GeoBench_968", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 0 + }, + { + "global index": "LiveCodeBench_105", + "flip": 1 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 0 + }, + { + "global index": "LiveCodeBench_131", + "flip": 0 + }, + { + "global index": "LiveCodeBench_136", + "flip": 0 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 0 + }, + { + "global index": "LiveCodeBench_271", + "flip": 1 + }, + { + "global index": "LiveCodeBench_350", + "flip": 0 + }, + { + "global index": "LiveCodeBench_386", + "flip": 0 + }, + { + "global index": "LiveCodeBench_405", + "flip": 0 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 0 + }, + { + "global index": "LiveCodeBench_437", + "flip": 0 + }, + { + "global index": "LiveCodeBench_476", + "flip": 0 + }, + { + "global index": "LiveCodeBench_485", + "flip": 0 + }, + { + "global index": "LiveCodeBench_49", + "flip": 0 + }, + { + "global index": "LiveCodeBench_491", + "flip": 0 + }, + { + "global index": "LiveCodeBench_499", + "flip": 1 + }, + { + "global index": "MATH_108", + "flip": 1 + }, + { + "global index": "MATH_442", + "flip": 1 + }, + { + "global index": "MATH_53", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 0 + }, + { + "global index": "MMLUPro_business_226", + "flip": 1 + }, + { + "global index": "MMLUPro_business_294", + "flip": 1 + }, + { + "global index": "MMLUPro_business_378", + "flip": 1 + }, + { + "global index": "MMLUPro_business_430", + "flip": 0 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 0 + }, + { + "global index": "MMLUPro_business_6", + "flip": 0 + }, + { + "global index": "MMLUPro_business_784", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 0 + }, + { + "global index": "MMLUPro_law_806", + "flip": 0 + }, + { + "global index": "MMLUPro_law_899", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 0 + }, + { + "global index": "MMLU_management_41", + "flip": 0 + }, + { + "global index": "MMLU_management_77", + "flip": 0 + }, + { + "global index": "MMLU_management_91", + "flip": 0 + }, + { + "global index": "MMLU_management_93", + "flip": 0 + }, + { + "global index": "MathQA_158", + "flip": 1 + }, + { + "global index": "MathQA_1742", + "flip": 0 + }, + { + "global index": "MathQA_202", + "flip": 1 + }, + { + "global index": "MathQA_2092", + "flip": 0 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 0 + }, + { + "global index": "MathQA_84", + "flip": 0 + }, + { + "global index": "MedMCQA_1005", + "flip": 0 + }, + { + "global index": "MedMCQA_1054", + "flip": 0 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 0 + }, + { + "global index": "MedMCQA_1362", + "flip": 0 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 0 + }, + { + "global index": "MedMCQA_2323", + "flip": 0 + }, + { + "global index": "MedMCQA_2366", + "flip": 1 + }, + { + "global index": "MedMCQA_2581", + "flip": 0 + }, + { + "global index": "MedMCQA_511", + "flip": 0 + }, + { + "global index": "MedMCQA_59", + "flip": 0 + }, + { + "global index": "MedMCQA_643", + "flip": 0 + }, + { + "global index": "MedMCQA_853", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 0 + }, + { + "global index": "NarrativeQA_1683", + "flip": 0 + }, + { + "global index": "NarrativeQA_2474", + "flip": 0 + }, + { + "global index": "NarrativeQA_2820", + "flip": 1 + }, + { + "global index": "NarrativeQA_3282", + "flip": 1 + }, + { + "global index": "NarrativeQA_4102", + "flip": 0 + }, + { + "global index": "NarrativeQA_4128", + "flip": 0 + }, + { + "global index": "NarrativeQA_4347", + "flip": 0 + }, + { + "global index": "NarrativeQA_4540", + "flip": 0 + }, + { + "global index": "NarrativeQA_5022", + "flip": 1 + }, + { + "global index": "NarrativeQA_5259", + "flip": 0 + }, + { + "global index": "NarrativeQA_533", + "flip": 0 + }, + { + "global index": "NarrativeQA_5894", + "flip": 0 + }, + { + "global index": "NarrativeQA_6829", + "flip": 1 + }, + { + "global index": "NarrativeQA_7678", + "flip": 0 + }, + { + "global index": "NarrativeQA_7964", + "flip": 0 + }, + { + "global index": "NarrativeQA_8215", + "flip": 0 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 0 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 0 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 1 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 0 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 0 + }, + { + "global index": "PubMedQA_0", + "flip": 0 + }, + { + "global index": "PubMedQA_154", + "flip": 0 + }, + { + "global index": "PubMedQA_18", + "flip": 0 + }, + { + "global index": "PubMedQA_238", + "flip": 0 + }, + { + "global index": "PubMedQA_250", + "flip": 0 + }, + { + "global index": "PubMedQA_337", + "flip": 0 + }, + { + "global index": "PubMedQA_362", + "flip": 0 + }, + { + "global index": "PubMedQA_437", + "flip": 0 + }, + { + "global index": "PubMedQA_510", + "flip": 0 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 0 + }, + { + "global index": "PubMedQA_582", + "flip": 0 + }, + { + "global index": "PubMedQA_588", + "flip": 0 + }, + { + "global index": "PubMedQA_610", + "flip": 0 + }, + { + "global index": "PubMedQA_63", + "flip": 0 + }, + { + "global index": "PubMedQA_643", + "flip": 0 + }, + { + "global index": "PubMedQA_687", + "flip": 0 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 0 + }, + { + "global index": "PubMedQA_755", + "flip": 0 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 0 + }, + { + "global index": "PubMedQA_854", + "flip": 0 + }, + { + "global index": "PubMedQA_905", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 0 + }, + { + "global index": "QANTA_Geography_304", + "flip": 0 + }, + { + "global index": "QANTA_History_1084", + "flip": 0 + }, + { + "global index": "QANTA_History_1154", + "flip": 0 + }, + { + "global index": "QANTA_History_433", + "flip": 0 + }, + { + "global index": "QANTA_History_473", + "flip": 0 + }, + { + "global index": "QANTA_History_926", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 0 + }, + { + "global index": "QANTA_Literature_386", + "flip": 0 + }, + { + "global index": "QANTA_Literature_408", + "flip": 0 + }, + { + "global index": "QANTA_Literature_475", + "flip": 0 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 0 + }, + { + "global index": "QANTA_Science_1360", + "flip": 0 + }, + { + "global index": "QANTA_Science_1473", + "flip": 0 + }, + { + "global index": "QANTA_Science_308", + "flip": 1 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 0 + }, + { + "global index": "SocialiQA_13810", + "flip": 0 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 0 + }, + { + "global index": "SocialiQA_7839", + "flip": 0 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 1 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 1 + }, + { + "global index": "WMT19-de-en_46", + "flip": 1 + }, + { + "global index": "WMT19-de-en_715", + "flip": 1 + }, + { + "global index": "WMT19-de-en_883", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 1 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 1 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 1 + } +] \ No newline at end of file diff --git a/src/data/flip_labels/flip_labels_kmeans.json b/src/data/flip_labels/flip_labels_kmeans.json new file mode 100644 index 0000000..56df69e --- /dev/null +++ b/src/data/flip_labels/flip_labels_kmeans.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 0 + }, + { + "global index": "AIME_58", + "flip": 0 + }, + { + "global index": "ArcMMLU_12", + "flip": 0 + }, + { + "global index": "ArcMMLU_123", + "flip": 0 + }, + { + "global index": "ArcMMLU_16", + "flip": 0 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 0 + }, + { + "global index": "ArcMMLU_293", + "flip": 0 + }, + { + "global index": "ArcMMLU_349", + "flip": 0 + }, + { + "global index": "ArcMMLU_378", + "flip": 0 + }, + { + "global index": "ArcMMLU_443", + "flip": 0 + }, + { + "global index": "ArcMMLU_496", + "flip": 0 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 0 + }, + { + "global index": "ArcMMLU_676", + "flip": 0 + }, + { + "global index": "ArcMMLU_685", + "flip": 0 + }, + { + "global index": "ArcMMLU_689", + "flip": 0 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 0 + }, + { + "global index": "ArcMMLU_98", + "flip": 0 + }, + { + "global index": "AsDiv_1165", + "flip": 1 + }, + { + "global index": "AsDiv_1347", + "flip": 0 + }, + { + "global index": "AsDiv_472", + "flip": 0 + }, + { + "global index": "AsDiv_733", + "flip": 0 + }, + { + "global index": "ChessInstruct_0", + "flip": 0 + }, + { + "global index": "ChessInstruct_107", + "flip": 0 + }, + { + "global index": "ChessInstruct_144", + "flip": 0 + }, + { + "global index": "ChessInstruct_42", + "flip": 0 + }, + { + "global index": "ChessInstruct_58", + "flip": 0 + }, + { + "global index": "ChessInstruct_71", + "flip": 0 + }, + { + "global index": "ChessInstruct_84", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 0 + }, + { + "global index": "Ethics_deontology_0", + "flip": 1 + }, + { + "global index": "Ethics_deontology_2", + "flip": 0 + }, + { + "global index": "Ethics_deontology_31", + "flip": 0 + }, + { + "global index": "Ethics_deontology_32", + "flip": 0 + }, + { + "global index": "Ethics_deontology_56", + "flip": 0 + }, + { + "global index": "Ethics_justice_1", + "flip": 1 + }, + { + "global index": "Ethics_justice_45", + "flip": 0 + }, + { + "global index": "Ethics_justice_76", + "flip": 0 + }, + { + "global index": "Ethics_justice_84", + "flip": 0 + }, + { + "global index": "Ethics_virtue_14", + "flip": 0 + }, + { + "global index": "Ethics_virtue_26", + "flip": 0 + }, + { + "global index": "Ethics_virtue_30", + "flip": 0 + }, + { + "global index": "Ethics_virtue_48", + "flip": 0 + }, + { + "global index": "Ethics_virtue_51", + "flip": 0 + }, + { + "global index": "FinQA_149", + "flip": 1 + }, + { + "global index": "FinQA_208", + "flip": 1 + }, + { + "global index": "FinQA_56", + "flip": 1 + }, + { + "global index": "FinQA_60", + "flip": 0 + }, + { + "global index": "GSM8K_43", + "flip": 1 + }, + { + "global index": "GeoBench_1002", + "flip": 0 + }, + { + "global index": "GeoBench_1094", + "flip": 1 + }, + { + "global index": "GeoBench_1102", + "flip": 1 + }, + { + "global index": "GeoBench_1113", + "flip": 1 + }, + { + "global index": "GeoBench_124", + "flip": 0 + }, + { + "global index": "GeoBench_1243", + "flip": 0 + }, + { + "global index": "GeoBench_30", + "flip": 0 + }, + { + "global index": "GeoBench_502", + "flip": 0 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 0 + }, + { + "global index": "GeoBench_766", + "flip": 0 + }, + { + "global index": "GeoBench_87", + "flip": 0 + }, + { + "global index": "GeoBench_915", + "flip": 0 + }, + { + "global index": "GeoBench_944", + "flip": 0 + }, + { + "global index": "GeoBench_968", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 0 + }, + { + "global index": "LiveCodeBench_105", + "flip": 0 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 0 + }, + { + "global index": "LiveCodeBench_131", + "flip": 0 + }, + { + "global index": "LiveCodeBench_136", + "flip": 0 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 0 + }, + { + "global index": "LiveCodeBench_271", + "flip": 0 + }, + { + "global index": "LiveCodeBench_350", + "flip": 0 + }, + { + "global index": "LiveCodeBench_386", + "flip": 0 + }, + { + "global index": "LiveCodeBench_405", + "flip": 0 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 0 + }, + { + "global index": "LiveCodeBench_437", + "flip": 0 + }, + { + "global index": "LiveCodeBench_476", + "flip": 0 + }, + { + "global index": "LiveCodeBench_485", + "flip": 0 + }, + { + "global index": "LiveCodeBench_49", + "flip": 0 + }, + { + "global index": "LiveCodeBench_491", + "flip": 0 + }, + { + "global index": "LiveCodeBench_499", + "flip": 0 + }, + { + "global index": "MATH_108", + "flip": 0 + }, + { + "global index": "MATH_442", + "flip": 0 + }, + { + "global index": "MATH_53", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 0 + }, + { + "global index": "MMLUPro_business_226", + "flip": 0 + }, + { + "global index": "MMLUPro_business_294", + "flip": 0 + }, + { + "global index": "MMLUPro_business_378", + "flip": 0 + }, + { + "global index": "MMLUPro_business_430", + "flip": 0 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 0 + }, + { + "global index": "MMLUPro_business_6", + "flip": 0 + }, + { + "global index": "MMLUPro_business_784", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 0 + }, + { + "global index": "MMLUPro_law_806", + "flip": 0 + }, + { + "global index": "MMLUPro_law_899", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 1 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 1 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 0 + }, + { + "global index": "MMLU_management_41", + "flip": 0 + }, + { + "global index": "MMLU_management_77", + "flip": 0 + }, + { + "global index": "MMLU_management_91", + "flip": 0 + }, + { + "global index": "MMLU_management_93", + "flip": 0 + }, + { + "global index": "MathQA_158", + "flip": 0 + }, + { + "global index": "MathQA_1742", + "flip": 0 + }, + { + "global index": "MathQA_202", + "flip": 0 + }, + { + "global index": "MathQA_2092", + "flip": 0 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 0 + }, + { + "global index": "MathQA_84", + "flip": 0 + }, + { + "global index": "MedMCQA_1005", + "flip": 0 + }, + { + "global index": "MedMCQA_1054", + "flip": 0 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 0 + }, + { + "global index": "MedMCQA_1362", + "flip": 0 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 1 + }, + { + "global index": "MedMCQA_2323", + "flip": 0 + }, + { + "global index": "MedMCQA_2366", + "flip": 0 + }, + { + "global index": "MedMCQA_2581", + "flip": 0 + }, + { + "global index": "MedMCQA_511", + "flip": 0 + }, + { + "global index": "MedMCQA_59", + "flip": 1 + }, + { + "global index": "MedMCQA_643", + "flip": 0 + }, + { + "global index": "MedMCQA_853", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 1 + }, + { + "global index": "NarrativeQA_1683", + "flip": 1 + }, + { + "global index": "NarrativeQA_2474", + "flip": 0 + }, + { + "global index": "NarrativeQA_2820", + "flip": 1 + }, + { + "global index": "NarrativeQA_3282", + "flip": 1 + }, + { + "global index": "NarrativeQA_4102", + "flip": 0 + }, + { + "global index": "NarrativeQA_4128", + "flip": 0 + }, + { + "global index": "NarrativeQA_4347", + "flip": 0 + }, + { + "global index": "NarrativeQA_4540", + "flip": 0 + }, + { + "global index": "NarrativeQA_5022", + "flip": 0 + }, + { + "global index": "NarrativeQA_5259", + "flip": 1 + }, + { + "global index": "NarrativeQA_533", + "flip": 0 + }, + { + "global index": "NarrativeQA_5894", + "flip": 0 + }, + { + "global index": "NarrativeQA_6829", + "flip": 0 + }, + { + "global index": "NarrativeQA_7678", + "flip": 1 + }, + { + "global index": "NarrativeQA_7964", + "flip": 1 + }, + { + "global index": "NarrativeQA_8215", + "flip": 1 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 1 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 0 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 0 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 0 + }, + { + "global index": "PubMedQA_0", + "flip": 1 + }, + { + "global index": "PubMedQA_154", + "flip": 0 + }, + { + "global index": "PubMedQA_18", + "flip": 0 + }, + { + "global index": "PubMedQA_238", + "flip": 1 + }, + { + "global index": "PubMedQA_250", + "flip": 0 + }, + { + "global index": "PubMedQA_337", + "flip": 0 + }, + { + "global index": "PubMedQA_362", + "flip": 0 + }, + { + "global index": "PubMedQA_437", + "flip": 1 + }, + { + "global index": "PubMedQA_510", + "flip": 0 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 0 + }, + { + "global index": "PubMedQA_582", + "flip": 0 + }, + { + "global index": "PubMedQA_588", + "flip": 0 + }, + { + "global index": "PubMedQA_610", + "flip": 1 + }, + { + "global index": "PubMedQA_63", + "flip": 0 + }, + { + "global index": "PubMedQA_643", + "flip": 1 + }, + { + "global index": "PubMedQA_687", + "flip": 0 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 0 + }, + { + "global index": "PubMedQA_755", + "flip": 0 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 0 + }, + { + "global index": "PubMedQA_854", + "flip": 0 + }, + { + "global index": "PubMedQA_905", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 1 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 0 + }, + { + "global index": "QANTA_Geography_304", + "flip": 0 + }, + { + "global index": "QANTA_History_1084", + "flip": 1 + }, + { + "global index": "QANTA_History_1154", + "flip": 0 + }, + { + "global index": "QANTA_History_433", + "flip": 1 + }, + { + "global index": "QANTA_History_473", + "flip": 0 + }, + { + "global index": "QANTA_History_926", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 0 + }, + { + "global index": "QANTA_Literature_386", + "flip": 1 + }, + { + "global index": "QANTA_Literature_408", + "flip": 0 + }, + { + "global index": "QANTA_Literature_475", + "flip": 1 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 1 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 0 + }, + { + "global index": "QANTA_Science_1360", + "flip": 0 + }, + { + "global index": "QANTA_Science_1473", + "flip": 0 + }, + { + "global index": "QANTA_Science_308", + "flip": 1 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 0 + }, + { + "global index": "SocialiQA_13810", + "flip": 0 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 0 + }, + { + "global index": "SocialiQA_7839", + "flip": 0 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 1 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 1 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 0 + }, + { + "global index": "WMT19-de-en_46", + "flip": 0 + }, + { + "global index": "WMT19-de-en_715", + "flip": 0 + }, + { + "global index": "WMT19-de-en_883", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 0 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 0 + } +] \ No newline at end of file diff --git a/src/data/flip_labels/flip_labels_knn.json b/src/data/flip_labels/flip_labels_knn.json new file mode 100644 index 0000000..b6fbe11 --- /dev/null +++ b/src/data/flip_labels/flip_labels_knn.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 1 + }, + { + "global index": "AIME_58", + "flip": 0 + }, + { + "global index": "ArcMMLU_12", + "flip": 0 + }, + { + "global index": "ArcMMLU_123", + "flip": 0 + }, + { + "global index": "ArcMMLU_16", + "flip": 0 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 0 + }, + { + "global index": "ArcMMLU_293", + "flip": 1 + }, + { + "global index": "ArcMMLU_349", + "flip": 1 + }, + { + "global index": "ArcMMLU_378", + "flip": 0 + }, + { + "global index": "ArcMMLU_443", + "flip": 1 + }, + { + "global index": "ArcMMLU_496", + "flip": 1 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 1 + }, + { + "global index": "ArcMMLU_676", + "flip": 0 + }, + { + "global index": "ArcMMLU_685", + "flip": 0 + }, + { + "global index": "ArcMMLU_689", + "flip": 0 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 0 + }, + { + "global index": "ArcMMLU_98", + "flip": 0 + }, + { + "global index": "AsDiv_1165", + "flip": 0 + }, + { + "global index": "AsDiv_1347", + "flip": 1 + }, + { + "global index": "AsDiv_472", + "flip": 0 + }, + { + "global index": "AsDiv_733", + "flip": 0 + }, + { + "global index": "ChessInstruct_0", + "flip": 0 + }, + { + "global index": "ChessInstruct_107", + "flip": 0 + }, + { + "global index": "ChessInstruct_144", + "flip": 0 + }, + { + "global index": "ChessInstruct_42", + "flip": 0 + }, + { + "global index": "ChessInstruct_58", + "flip": 0 + }, + { + "global index": "ChessInstruct_71", + "flip": 0 + }, + { + "global index": "ChessInstruct_84", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 0 + }, + { + "global index": "Ethics_deontology_0", + "flip": 0 + }, + { + "global index": "Ethics_deontology_2", + "flip": 0 + }, + { + "global index": "Ethics_deontology_31", + "flip": 0 + }, + { + "global index": "Ethics_deontology_32", + "flip": 0 + }, + { + "global index": "Ethics_deontology_56", + "flip": 0 + }, + { + "global index": "Ethics_justice_1", + "flip": 0 + }, + { + "global index": "Ethics_justice_45", + "flip": 0 + }, + { + "global index": "Ethics_justice_76", + "flip": 0 + }, + { + "global index": "Ethics_justice_84", + "flip": 0 + }, + { + "global index": "Ethics_virtue_14", + "flip": 0 + }, + { + "global index": "Ethics_virtue_26", + "flip": 0 + }, + { + "global index": "Ethics_virtue_30", + "flip": 0 + }, + { + "global index": "Ethics_virtue_48", + "flip": 0 + }, + { + "global index": "Ethics_virtue_51", + "flip": 0 + }, + { + "global index": "FinQA_149", + "flip": 0 + }, + { + "global index": "FinQA_208", + "flip": 0 + }, + { + "global index": "FinQA_56", + "flip": 0 + }, + { + "global index": "FinQA_60", + "flip": 0 + }, + { + "global index": "GSM8K_43", + "flip": 0 + }, + { + "global index": "GeoBench_1002", + "flip": 0 + }, + { + "global index": "GeoBench_1094", + "flip": 1 + }, + { + "global index": "GeoBench_1102", + "flip": 1 + }, + { + "global index": "GeoBench_1113", + "flip": 1 + }, + { + "global index": "GeoBench_124", + "flip": 1 + }, + { + "global index": "GeoBench_1243", + "flip": 1 + }, + { + "global index": "GeoBench_30", + "flip": 0 + }, + { + "global index": "GeoBench_502", + "flip": 1 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 1 + }, + { + "global index": "GeoBench_766", + "flip": 0 + }, + { + "global index": "GeoBench_87", + "flip": 0 + }, + { + "global index": "GeoBench_915", + "flip": 0 + }, + { + "global index": "GeoBench_944", + "flip": 0 + }, + { + "global index": "GeoBench_968", + "flip": 1 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 0 + }, + { + "global index": "LiveCodeBench_105", + "flip": 0 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 1 + }, + { + "global index": "LiveCodeBench_131", + "flip": 0 + }, + { + "global index": "LiveCodeBench_136", + "flip": 0 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 0 + }, + { + "global index": "LiveCodeBench_271", + "flip": 0 + }, + { + "global index": "LiveCodeBench_350", + "flip": 0 + }, + { + "global index": "LiveCodeBench_386", + "flip": 1 + }, + { + "global index": "LiveCodeBench_405", + "flip": 0 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 0 + }, + { + "global index": "LiveCodeBench_437", + "flip": 0 + }, + { + "global index": "LiveCodeBench_476", + "flip": 0 + }, + { + "global index": "LiveCodeBench_485", + "flip": 0 + }, + { + "global index": "LiveCodeBench_49", + "flip": 0 + }, + { + "global index": "LiveCodeBench_491", + "flip": 1 + }, + { + "global index": "LiveCodeBench_499", + "flip": 0 + }, + { + "global index": "MATH_108", + "flip": 0 + }, + { + "global index": "MATH_442", + "flip": 0 + }, + { + "global index": "MATH_53", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 1 + }, + { + "global index": "MMLUPro_business_226", + "flip": 1 + }, + { + "global index": "MMLUPro_business_294", + "flip": 1 + }, + { + "global index": "MMLUPro_business_378", + "flip": 0 + }, + { + "global index": "MMLUPro_business_430", + "flip": 1 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 1 + }, + { + "global index": "MMLUPro_business_6", + "flip": 1 + }, + { + "global index": "MMLUPro_business_784", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 1 + }, + { + "global index": "MMLUPro_law_806", + "flip": 0 + }, + { + "global index": "MMLUPro_law_899", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 1 + }, + { + "global index": "MMLU_management_41", + "flip": 0 + }, + { + "global index": "MMLU_management_77", + "flip": 0 + }, + { + "global index": "MMLU_management_91", + "flip": 0 + }, + { + "global index": "MMLU_management_93", + "flip": 1 + }, + { + "global index": "MathQA_158", + "flip": 0 + }, + { + "global index": "MathQA_1742", + "flip": 1 + }, + { + "global index": "MathQA_202", + "flip": 0 + }, + { + "global index": "MathQA_2092", + "flip": 0 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 0 + }, + { + "global index": "MathQA_84", + "flip": 0 + }, + { + "global index": "MedMCQA_1005", + "flip": 0 + }, + { + "global index": "MedMCQA_1054", + "flip": 0 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 0 + }, + { + "global index": "MedMCQA_1362", + "flip": 1 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 0 + }, + { + "global index": "MedMCQA_2323", + "flip": 0 + }, + { + "global index": "MedMCQA_2366", + "flip": 0 + }, + { + "global index": "MedMCQA_2581", + "flip": 0 + }, + { + "global index": "MedMCQA_511", + "flip": 1 + }, + { + "global index": "MedMCQA_59", + "flip": 0 + }, + { + "global index": "MedMCQA_643", + "flip": 1 + }, + { + "global index": "MedMCQA_853", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 0 + }, + { + "global index": "NarrativeQA_1683", + "flip": 0 + }, + { + "global index": "NarrativeQA_2474", + "flip": 0 + }, + { + "global index": "NarrativeQA_2820", + "flip": 0 + }, + { + "global index": "NarrativeQA_3282", + "flip": 0 + }, + { + "global index": "NarrativeQA_4102", + "flip": 0 + }, + { + "global index": "NarrativeQA_4128", + "flip": 0 + }, + { + "global index": "NarrativeQA_4347", + "flip": 1 + }, + { + "global index": "NarrativeQA_4540", + "flip": 0 + }, + { + "global index": "NarrativeQA_5022", + "flip": 0 + }, + { + "global index": "NarrativeQA_5259", + "flip": 1 + }, + { + "global index": "NarrativeQA_533", + "flip": 0 + }, + { + "global index": "NarrativeQA_5894", + "flip": 0 + }, + { + "global index": "NarrativeQA_6829", + "flip": 1 + }, + { + "global index": "NarrativeQA_7678", + "flip": 0 + }, + { + "global index": "NarrativeQA_7964", + "flip": 0 + }, + { + "global index": "NarrativeQA_8215", + "flip": 0 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 1 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 0 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 0 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 1 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 0 + }, + { + "global index": "PubMedQA_0", + "flip": 0 + }, + { + "global index": "PubMedQA_154", + "flip": 0 + }, + { + "global index": "PubMedQA_18", + "flip": 0 + }, + { + "global index": "PubMedQA_238", + "flip": 1 + }, + { + "global index": "PubMedQA_250", + "flip": 0 + }, + { + "global index": "PubMedQA_337", + "flip": 0 + }, + { + "global index": "PubMedQA_362", + "flip": 0 + }, + { + "global index": "PubMedQA_437", + "flip": 0 + }, + { + "global index": "PubMedQA_510", + "flip": 0 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 1 + }, + { + "global index": "PubMedQA_582", + "flip": 0 + }, + { + "global index": "PubMedQA_588", + "flip": 0 + }, + { + "global index": "PubMedQA_610", + "flip": 0 + }, + { + "global index": "PubMedQA_63", + "flip": 0 + }, + { + "global index": "PubMedQA_643", + "flip": 0 + }, + { + "global index": "PubMedQA_687", + "flip": 0 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 0 + }, + { + "global index": "PubMedQA_755", + "flip": 0 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 0 + }, + { + "global index": "PubMedQA_854", + "flip": 0 + }, + { + "global index": "PubMedQA_905", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 0 + }, + { + "global index": "QANTA_Geography_304", + "flip": 0 + }, + { + "global index": "QANTA_History_1084", + "flip": 0 + }, + { + "global index": "QANTA_History_1154", + "flip": 0 + }, + { + "global index": "QANTA_History_433", + "flip": 1 + }, + { + "global index": "QANTA_History_473", + "flip": 0 + }, + { + "global index": "QANTA_History_926", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 0 + }, + { + "global index": "QANTA_Literature_386", + "flip": 0 + }, + { + "global index": "QANTA_Literature_408", + "flip": 0 + }, + { + "global index": "QANTA_Literature_475", + "flip": 0 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 1 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 0 + }, + { + "global index": "QANTA_Science_1360", + "flip": 0 + }, + { + "global index": "QANTA_Science_1473", + "flip": 0 + }, + { + "global index": "QANTA_Science_308", + "flip": 0 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 0 + }, + { + "global index": "SocialiQA_13810", + "flip": 0 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 1 + }, + { + "global index": "SocialiQA_7839", + "flip": 0 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 0 + }, + { + "global index": "WMT19-de-en_46", + "flip": 0 + }, + { + "global index": "WMT19-de-en_715", + "flip": 0 + }, + { + "global index": "WMT19-de-en_883", + "flip": 1 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 0 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 0 + } +] \ No newline at end of file diff --git a/src/data/flip_labels/flip_labels_mirt.json b/src/data/flip_labels/flip_labels_mirt.json new file mode 100644 index 0000000..a17bb28 --- /dev/null +++ b/src/data/flip_labels/flip_labels_mirt.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 0 + }, + { + "global index": "AIME_58", + "flip": 0 + }, + { + "global index": "ArcMMLU_12", + "flip": 0 + }, + { + "global index": "ArcMMLU_123", + "flip": 0 + }, + { + "global index": "ArcMMLU_16", + "flip": 0 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 0 + }, + { + "global index": "ArcMMLU_293", + "flip": 0 + }, + { + "global index": "ArcMMLU_349", + "flip": 0 + }, + { + "global index": "ArcMMLU_378", + "flip": 1 + }, + { + "global index": "ArcMMLU_443", + "flip": 0 + }, + { + "global index": "ArcMMLU_496", + "flip": 0 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 0 + }, + { + "global index": "ArcMMLU_676", + "flip": 0 + }, + { + "global index": "ArcMMLU_685", + "flip": 1 + }, + { + "global index": "ArcMMLU_689", + "flip": 1 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 0 + }, + { + "global index": "ArcMMLU_98", + "flip": 1 + }, + { + "global index": "AsDiv_1165", + "flip": 0 + }, + { + "global index": "AsDiv_1347", + "flip": 0 + }, + { + "global index": "AsDiv_472", + "flip": 1 + }, + { + "global index": "AsDiv_733", + "flip": 1 + }, + { + "global index": "ChessInstruct_0", + "flip": 0 + }, + { + "global index": "ChessInstruct_107", + "flip": 0 + }, + { + "global index": "ChessInstruct_144", + "flip": 0 + }, + { + "global index": "ChessInstruct_42", + "flip": 0 + }, + { + "global index": "ChessInstruct_58", + "flip": 0 + }, + { + "global index": "ChessInstruct_71", + "flip": 0 + }, + { + "global index": "ChessInstruct_84", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 1 + }, + { + "global index": "Ethics_deontology_0", + "flip": 1 + }, + { + "global index": "Ethics_deontology_2", + "flip": 0 + }, + { + "global index": "Ethics_deontology_31", + "flip": 1 + }, + { + "global index": "Ethics_deontology_32", + "flip": 1 + }, + { + "global index": "Ethics_deontology_56", + "flip": 1 + }, + { + "global index": "Ethics_justice_1", + "flip": 1 + }, + { + "global index": "Ethics_justice_45", + "flip": 1 + }, + { + "global index": "Ethics_justice_76", + "flip": 1 + }, + { + "global index": "Ethics_justice_84", + "flip": 1 + }, + { + "global index": "Ethics_virtue_14", + "flip": 0 + }, + { + "global index": "Ethics_virtue_26", + "flip": 0 + }, + { + "global index": "Ethics_virtue_30", + "flip": 1 + }, + { + "global index": "Ethics_virtue_48", + "flip": 1 + }, + { + "global index": "Ethics_virtue_51", + "flip": 1 + }, + { + "global index": "FinQA_149", + "flip": 0 + }, + { + "global index": "FinQA_208", + "flip": 0 + }, + { + "global index": "FinQA_56", + "flip": 0 + }, + { + "global index": "FinQA_60", + "flip": 0 + }, + { + "global index": "GSM8K_43", + "flip": 1 + }, + { + "global index": "GeoBench_1002", + "flip": 1 + }, + { + "global index": "GeoBench_1094", + "flip": 1 + }, + { + "global index": "GeoBench_1102", + "flip": 1 + }, + { + "global index": "GeoBench_1113", + "flip": 1 + }, + { + "global index": "GeoBench_124", + "flip": 0 + }, + { + "global index": "GeoBench_1243", + "flip": 1 + }, + { + "global index": "GeoBench_30", + "flip": 1 + }, + { + "global index": "GeoBench_502", + "flip": 1 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 0 + }, + { + "global index": "GeoBench_766", + "flip": 1 + }, + { + "global index": "GeoBench_87", + "flip": 1 + }, + { + "global index": "GeoBench_915", + "flip": 0 + }, + { + "global index": "GeoBench_944", + "flip": 1 + }, + { + "global index": "GeoBench_968", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 1 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 1 + }, + { + "global index": "LiveCodeBench_105", + "flip": 0 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 0 + }, + { + "global index": "LiveCodeBench_131", + "flip": 0 + }, + { + "global index": "LiveCodeBench_136", + "flip": 1 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 0 + }, + { + "global index": "LiveCodeBench_271", + "flip": 0 + }, + { + "global index": "LiveCodeBench_350", + "flip": 0 + }, + { + "global index": "LiveCodeBench_386", + "flip": 0 + }, + { + "global index": "LiveCodeBench_405", + "flip": 0 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 0 + }, + { + "global index": "LiveCodeBench_437", + "flip": 0 + }, + { + "global index": "LiveCodeBench_476", + "flip": 1 + }, + { + "global index": "LiveCodeBench_485", + "flip": 0 + }, + { + "global index": "LiveCodeBench_49", + "flip": 0 + }, + { + "global index": "LiveCodeBench_491", + "flip": 0 + }, + { + "global index": "LiveCodeBench_499", + "flip": 0 + }, + { + "global index": "MATH_108", + "flip": 0 + }, + { + "global index": "MATH_442", + "flip": 1 + }, + { + "global index": "MATH_53", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 1 + }, + { + "global index": "MMLUPro_business_226", + "flip": 0 + }, + { + "global index": "MMLUPro_business_294", + "flip": 0 + }, + { + "global index": "MMLUPro_business_378", + "flip": 0 + }, + { + "global index": "MMLUPro_business_430", + "flip": 0 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 0 + }, + { + "global index": "MMLUPro_business_6", + "flip": 0 + }, + { + "global index": "MMLUPro_business_784", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 1 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 0 + }, + { + "global index": "MMLUPro_law_806", + "flip": 0 + }, + { + "global index": "MMLUPro_law_899", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 1 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 1 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 1 + }, + { + "global index": "MMLU_management_41", + "flip": 1 + }, + { + "global index": "MMLU_management_77", + "flip": 0 + }, + { + "global index": "MMLU_management_91", + "flip": 0 + }, + { + "global index": "MMLU_management_93", + "flip": 0 + }, + { + "global index": "MathQA_158", + "flip": 0 + }, + { + "global index": "MathQA_1742", + "flip": 0 + }, + { + "global index": "MathQA_202", + "flip": 0 + }, + { + "global index": "MathQA_2092", + "flip": 0 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 0 + }, + { + "global index": "MathQA_84", + "flip": 1 + }, + { + "global index": "MedMCQA_1005", + "flip": 0 + }, + { + "global index": "MedMCQA_1054", + "flip": 1 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 1 + }, + { + "global index": "MedMCQA_1362", + "flip": 0 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 0 + }, + { + "global index": "MedMCQA_2323", + "flip": 1 + }, + { + "global index": "MedMCQA_2366", + "flip": 1 + }, + { + "global index": "MedMCQA_2581", + "flip": 1 + }, + { + "global index": "MedMCQA_511", + "flip": 1 + }, + { + "global index": "MedMCQA_59", + "flip": 1 + }, + { + "global index": "MedMCQA_643", + "flip": 0 + }, + { + "global index": "MedMCQA_853", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 0 + }, + { + "global index": "NarrativeQA_1683", + "flip": 0 + }, + { + "global index": "NarrativeQA_2474", + "flip": 0 + }, + { + "global index": "NarrativeQA_2820", + "flip": 1 + }, + { + "global index": "NarrativeQA_3282", + "flip": 1 + }, + { + "global index": "NarrativeQA_4102", + "flip": 1 + }, + { + "global index": "NarrativeQA_4128", + "flip": 1 + }, + { + "global index": "NarrativeQA_4347", + "flip": 0 + }, + { + "global index": "NarrativeQA_4540", + "flip": 0 + }, + { + "global index": "NarrativeQA_5022", + "flip": 1 + }, + { + "global index": "NarrativeQA_5259", + "flip": 0 + }, + { + "global index": "NarrativeQA_533", + "flip": 0 + }, + { + "global index": "NarrativeQA_5894", + "flip": 0 + }, + { + "global index": "NarrativeQA_6829", + "flip": 1 + }, + { + "global index": "NarrativeQA_7678", + "flip": 1 + }, + { + "global index": "NarrativeQA_7964", + "flip": 0 + }, + { + "global index": "NarrativeQA_8215", + "flip": 0 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 1 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 1 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 1 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 1 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 1 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 1 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 1 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 0 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 1 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 1 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 1 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 1 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 1 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 0 + }, + { + "global index": "PubMedQA_0", + "flip": 0 + }, + { + "global index": "PubMedQA_154", + "flip": 0 + }, + { + "global index": "PubMedQA_18", + "flip": 0 + }, + { + "global index": "PubMedQA_238", + "flip": 1 + }, + { + "global index": "PubMedQA_250", + "flip": 0 + }, + { + "global index": "PubMedQA_337", + "flip": 0 + }, + { + "global index": "PubMedQA_362", + "flip": 0 + }, + { + "global index": "PubMedQA_437", + "flip": 1 + }, + { + "global index": "PubMedQA_510", + "flip": 0 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 1 + }, + { + "global index": "PubMedQA_582", + "flip": 0 + }, + { + "global index": "PubMedQA_588", + "flip": 1 + }, + { + "global index": "PubMedQA_610", + "flip": 1 + }, + { + "global index": "PubMedQA_63", + "flip": 0 + }, + { + "global index": "PubMedQA_643", + "flip": 0 + }, + { + "global index": "PubMedQA_687", + "flip": 0 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 0 + }, + { + "global index": "PubMedQA_755", + "flip": 1 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 1 + }, + { + "global index": "PubMedQA_854", + "flip": 0 + }, + { + "global index": "PubMedQA_905", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 1 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 1 + }, + { + "global index": "QANTA_Geography_304", + "flip": 1 + }, + { + "global index": "QANTA_History_1084", + "flip": 1 + }, + { + "global index": "QANTA_History_1154", + "flip": 1 + }, + { + "global index": "QANTA_History_433", + "flip": 1 + }, + { + "global index": "QANTA_History_473", + "flip": 1 + }, + { + "global index": "QANTA_History_926", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 0 + }, + { + "global index": "QANTA_Literature_386", + "flip": 1 + }, + { + "global index": "QANTA_Literature_408", + "flip": 1 + }, + { + "global index": "QANTA_Literature_475", + "flip": 1 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 1 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 0 + }, + { + "global index": "QANTA_Science_1360", + "flip": 0 + }, + { + "global index": "QANTA_Science_1473", + "flip": 1 + }, + { + "global index": "QANTA_Science_308", + "flip": 1 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 1 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 1 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 1 + }, + { + "global index": "SocialiQA_13810", + "flip": 0 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 0 + }, + { + "global index": "SocialiQA_7839", + "flip": 1 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 1 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 1 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 0 + }, + { + "global index": "WMT19-de-en_46", + "flip": 1 + }, + { + "global index": "WMT19-de-en_715", + "flip": 1 + }, + { + "global index": "WMT19-de-en_883", + "flip": 1 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 1 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 1 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 0 + } +] \ No newline at end of file diff --git a/src/data/flip_labels/flip_labels_mlp.json b/src/data/flip_labels/flip_labels_mlp.json new file mode 100644 index 0000000..5f59f9f --- /dev/null +++ b/src/data/flip_labels/flip_labels_mlp.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 0 + }, + { + "global index": "AIME_58", + "flip": 1 + }, + { + "global index": "ArcMMLU_12", + "flip": 0 + }, + { + "global index": "ArcMMLU_123", + "flip": 0 + }, + { + "global index": "ArcMMLU_16", + "flip": 0 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 0 + }, + { + "global index": "ArcMMLU_293", + "flip": 0 + }, + { + "global index": "ArcMMLU_349", + "flip": 0 + }, + { + "global index": "ArcMMLU_378", + "flip": 0 + }, + { + "global index": "ArcMMLU_443", + "flip": 0 + }, + { + "global index": "ArcMMLU_496", + "flip": 0 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 0 + }, + { + "global index": "ArcMMLU_676", + "flip": 0 + }, + { + "global index": "ArcMMLU_685", + "flip": 0 + }, + { + "global index": "ArcMMLU_689", + "flip": 0 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 0 + }, + { + "global index": "ArcMMLU_98", + "flip": 1 + }, + { + "global index": "AsDiv_1165", + "flip": 0 + }, + { + "global index": "AsDiv_1347", + "flip": 0 + }, + { + "global index": "AsDiv_472", + "flip": 0 + }, + { + "global index": "AsDiv_733", + "flip": 0 + }, + { + "global index": "ChessInstruct_0", + "flip": 1 + }, + { + "global index": "ChessInstruct_107", + "flip": 0 + }, + { + "global index": "ChessInstruct_144", + "flip": 0 + }, + { + "global index": "ChessInstruct_42", + "flip": 0 + }, + { + "global index": "ChessInstruct_58", + "flip": 0 + }, + { + "global index": "ChessInstruct_71", + "flip": 0 + }, + { + "global index": "ChessInstruct_84", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 0 + }, + { + "global index": "Ethics_deontology_0", + "flip": 0 + }, + { + "global index": "Ethics_deontology_2", + "flip": 0 + }, + { + "global index": "Ethics_deontology_31", + "flip": 1 + }, + { + "global index": "Ethics_deontology_32", + "flip": 0 + }, + { + "global index": "Ethics_deontology_56", + "flip": 0 + }, + { + "global index": "Ethics_justice_1", + "flip": 1 + }, + { + "global index": "Ethics_justice_45", + "flip": 0 + }, + { + "global index": "Ethics_justice_76", + "flip": 0 + }, + { + "global index": "Ethics_justice_84", + "flip": 0 + }, + { + "global index": "Ethics_virtue_14", + "flip": 0 + }, + { + "global index": "Ethics_virtue_26", + "flip": 0 + }, + { + "global index": "Ethics_virtue_30", + "flip": 0 + }, + { + "global index": "Ethics_virtue_48", + "flip": 0 + }, + { + "global index": "Ethics_virtue_51", + "flip": 0 + }, + { + "global index": "FinQA_149", + "flip": 0 + }, + { + "global index": "FinQA_208", + "flip": 1 + }, + { + "global index": "FinQA_56", + "flip": 0 + }, + { + "global index": "FinQA_60", + "flip": 0 + }, + { + "global index": "GSM8K_43", + "flip": 0 + }, + { + "global index": "GeoBench_1002", + "flip": 0 + }, + { + "global index": "GeoBench_1094", + "flip": 0 + }, + { + "global index": "GeoBench_1102", + "flip": 1 + }, + { + "global index": "GeoBench_1113", + "flip": 1 + }, + { + "global index": "GeoBench_124", + "flip": 0 + }, + { + "global index": "GeoBench_1243", + "flip": 0 + }, + { + "global index": "GeoBench_30", + "flip": 0 + }, + { + "global index": "GeoBench_502", + "flip": 0 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 0 + }, + { + "global index": "GeoBench_766", + "flip": 0 + }, + { + "global index": "GeoBench_87", + "flip": 1 + }, + { + "global index": "GeoBench_915", + "flip": 0 + }, + { + "global index": "GeoBench_944", + "flip": 1 + }, + { + "global index": "GeoBench_968", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 0 + }, + { + "global index": "LiveCodeBench_105", + "flip": 1 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 0 + }, + { + "global index": "LiveCodeBench_131", + "flip": 0 + }, + { + "global index": "LiveCodeBench_136", + "flip": 0 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 0 + }, + { + "global index": "LiveCodeBench_271", + "flip": 0 + }, + { + "global index": "LiveCodeBench_350", + "flip": 0 + }, + { + "global index": "LiveCodeBench_386", + "flip": 0 + }, + { + "global index": "LiveCodeBench_405", + "flip": 1 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 0 + }, + { + "global index": "LiveCodeBench_437", + "flip": 0 + }, + { + "global index": "LiveCodeBench_476", + "flip": 0 + }, + { + "global index": "LiveCodeBench_485", + "flip": 0 + }, + { + "global index": "LiveCodeBench_49", + "flip": 1 + }, + { + "global index": "LiveCodeBench_491", + "flip": 1 + }, + { + "global index": "LiveCodeBench_499", + "flip": 0 + }, + { + "global index": "MATH_108", + "flip": 1 + }, + { + "global index": "MATH_442", + "flip": 0 + }, + { + "global index": "MATH_53", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 0 + }, + { + "global index": "MMLUPro_business_226", + "flip": 1 + }, + { + "global index": "MMLUPro_business_294", + "flip": 0 + }, + { + "global index": "MMLUPro_business_378", + "flip": 0 + }, + { + "global index": "MMLUPro_business_430", + "flip": 0 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 0 + }, + { + "global index": "MMLUPro_business_6", + "flip": 0 + }, + { + "global index": "MMLUPro_business_784", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 1 + }, + { + "global index": "MMLUPro_law_806", + "flip": 0 + }, + { + "global index": "MMLUPro_law_899", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 1 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 1 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 1 + }, + { + "global index": "MMLU_management_41", + "flip": 0 + }, + { + "global index": "MMLU_management_77", + "flip": 0 + }, + { + "global index": "MMLU_management_91", + "flip": 0 + }, + { + "global index": "MMLU_management_93", + "flip": 0 + }, + { + "global index": "MathQA_158", + "flip": 0 + }, + { + "global index": "MathQA_1742", + "flip": 1 + }, + { + "global index": "MathQA_202", + "flip": 0 + }, + { + "global index": "MathQA_2092", + "flip": 0 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 0 + }, + { + "global index": "MathQA_84", + "flip": 0 + }, + { + "global index": "MedMCQA_1005", + "flip": 0 + }, + { + "global index": "MedMCQA_1054", + "flip": 0 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 0 + }, + { + "global index": "MedMCQA_1362", + "flip": 0 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 0 + }, + { + "global index": "MedMCQA_2323", + "flip": 0 + }, + { + "global index": "MedMCQA_2366", + "flip": 0 + }, + { + "global index": "MedMCQA_2581", + "flip": 0 + }, + { + "global index": "MedMCQA_511", + "flip": 0 + }, + { + "global index": "MedMCQA_59", + "flip": 0 + }, + { + "global index": "MedMCQA_643", + "flip": 0 + }, + { + "global index": "MedMCQA_853", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 1 + }, + { + "global index": "NarrativeQA_1683", + "flip": 0 + }, + { + "global index": "NarrativeQA_2474", + "flip": 1 + }, + { + "global index": "NarrativeQA_2820", + "flip": 1 + }, + { + "global index": "NarrativeQA_3282", + "flip": 1 + }, + { + "global index": "NarrativeQA_4102", + "flip": 0 + }, + { + "global index": "NarrativeQA_4128", + "flip": 1 + }, + { + "global index": "NarrativeQA_4347", + "flip": 1 + }, + { + "global index": "NarrativeQA_4540", + "flip": 0 + }, + { + "global index": "NarrativeQA_5022", + "flip": 1 + }, + { + "global index": "NarrativeQA_5259", + "flip": 0 + }, + { + "global index": "NarrativeQA_533", + "flip": 0 + }, + { + "global index": "NarrativeQA_5894", + "flip": 0 + }, + { + "global index": "NarrativeQA_6829", + "flip": 1 + }, + { + "global index": "NarrativeQA_7678", + "flip": 1 + }, + { + "global index": "NarrativeQA_7964", + "flip": 1 + }, + { + "global index": "NarrativeQA_8215", + "flip": 1 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 1 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 0 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 0 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 0 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 0 + }, + { + "global index": "PubMedQA_0", + "flip": 0 + }, + { + "global index": "PubMedQA_154", + "flip": 1 + }, + { + "global index": "PubMedQA_18", + "flip": 0 + }, + { + "global index": "PubMedQA_238", + "flip": 1 + }, + { + "global index": "PubMedQA_250", + "flip": 0 + }, + { + "global index": "PubMedQA_337", + "flip": 0 + }, + { + "global index": "PubMedQA_362", + "flip": 0 + }, + { + "global index": "PubMedQA_437", + "flip": 0 + }, + { + "global index": "PubMedQA_510", + "flip": 0 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 1 + }, + { + "global index": "PubMedQA_582", + "flip": 0 + }, + { + "global index": "PubMedQA_588", + "flip": 0 + }, + { + "global index": "PubMedQA_610", + "flip": 1 + }, + { + "global index": "PubMedQA_63", + "flip": 1 + }, + { + "global index": "PubMedQA_643", + "flip": 0 + }, + { + "global index": "PubMedQA_687", + "flip": 1 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 0 + }, + { + "global index": "PubMedQA_755", + "flip": 0 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 1 + }, + { + "global index": "PubMedQA_854", + "flip": 0 + }, + { + "global index": "PubMedQA_905", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 0 + }, + { + "global index": "QANTA_Geography_304", + "flip": 0 + }, + { + "global index": "QANTA_History_1084", + "flip": 0 + }, + { + "global index": "QANTA_History_1154", + "flip": 0 + }, + { + "global index": "QANTA_History_433", + "flip": 0 + }, + { + "global index": "QANTA_History_473", + "flip": 0 + }, + { + "global index": "QANTA_History_926", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 1 + }, + { + "global index": "QANTA_Literature_386", + "flip": 1 + }, + { + "global index": "QANTA_Literature_408", + "flip": 0 + }, + { + "global index": "QANTA_Literature_475", + "flip": 0 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 1 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 1 + }, + { + "global index": "QANTA_Science_1360", + "flip": 1 + }, + { + "global index": "QANTA_Science_1473", + "flip": 0 + }, + { + "global index": "QANTA_Science_308", + "flip": 0 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 1 + }, + { + "global index": "SocialiQA_13810", + "flip": 0 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 0 + }, + { + "global index": "SocialiQA_7839", + "flip": 0 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 1 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 1 + }, + { + "global index": "WMT19-de-en_46", + "flip": 1 + }, + { + "global index": "WMT19-de-en_715", + "flip": 0 + }, + { + "global index": "WMT19-de-en_883", + "flip": 1 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 1 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 1 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 0 + } +] \ No newline at end of file diff --git a/src/data/flip_labels/flip_labels_nirt.json b/src/data/flip_labels/flip_labels_nirt.json new file mode 100644 index 0000000..2b258a5 --- /dev/null +++ b/src/data/flip_labels/flip_labels_nirt.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 1 + }, + { + "global index": "AIME_58", + "flip": 1 + }, + { + "global index": "ArcMMLU_12", + "flip": 1 + }, + { + "global index": "ArcMMLU_123", + "flip": 1 + }, + { + "global index": "ArcMMLU_16", + "flip": 1 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 1 + }, + { + "global index": "ArcMMLU_293", + "flip": 1 + }, + { + "global index": "ArcMMLU_349", + "flip": 1 + }, + { + "global index": "ArcMMLU_378", + "flip": 0 + }, + { + "global index": "ArcMMLU_443", + "flip": 1 + }, + { + "global index": "ArcMMLU_496", + "flip": 0 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 1 + }, + { + "global index": "ArcMMLU_676", + "flip": 1 + }, + { + "global index": "ArcMMLU_685", + "flip": 1 + }, + { + "global index": "ArcMMLU_689", + "flip": 0 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 1 + }, + { + "global index": "ArcMMLU_98", + "flip": 1 + }, + { + "global index": "AsDiv_1165", + "flip": 0 + }, + { + "global index": "AsDiv_1347", + "flip": 0 + }, + { + "global index": "AsDiv_472", + "flip": 1 + }, + { + "global index": "AsDiv_733", + "flip": 0 + }, + { + "global index": "ChessInstruct_0", + "flip": 0 + }, + { + "global index": "ChessInstruct_107", + "flip": 1 + }, + { + "global index": "ChessInstruct_144", + "flip": 1 + }, + { + "global index": "ChessInstruct_42", + "flip": 0 + }, + { + "global index": "ChessInstruct_58", + "flip": 1 + }, + { + "global index": "ChessInstruct_71", + "flip": 1 + }, + { + "global index": "ChessInstruct_84", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 1 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 0 + }, + { + "global index": "Ethics_deontology_0", + "flip": 1 + }, + { + "global index": "Ethics_deontology_2", + "flip": 1 + }, + { + "global index": "Ethics_deontology_31", + "flip": 1 + }, + { + "global index": "Ethics_deontology_32", + "flip": 1 + }, + { + "global index": "Ethics_deontology_56", + "flip": 1 + }, + { + "global index": "Ethics_justice_1", + "flip": 1 + }, + { + "global index": "Ethics_justice_45", + "flip": 1 + }, + { + "global index": "Ethics_justice_76", + "flip": 1 + }, + { + "global index": "Ethics_justice_84", + "flip": 1 + }, + { + "global index": "Ethics_virtue_14", + "flip": 1 + }, + { + "global index": "Ethics_virtue_26", + "flip": 1 + }, + { + "global index": "Ethics_virtue_30", + "flip": 1 + }, + { + "global index": "Ethics_virtue_48", + "flip": 0 + }, + { + "global index": "Ethics_virtue_51", + "flip": 1 + }, + { + "global index": "FinQA_149", + "flip": 0 + }, + { + "global index": "FinQA_208", + "flip": 1 + }, + { + "global index": "FinQA_56", + "flip": 1 + }, + { + "global index": "FinQA_60", + "flip": 1 + }, + { + "global index": "GSM8K_43", + "flip": 1 + }, + { + "global index": "GeoBench_1002", + "flip": 0 + }, + { + "global index": "GeoBench_1094", + "flip": 0 + }, + { + "global index": "GeoBench_1102", + "flip": 1 + }, + { + "global index": "GeoBench_1113", + "flip": 1 + }, + { + "global index": "GeoBench_124", + "flip": 0 + }, + { + "global index": "GeoBench_1243", + "flip": 1 + }, + { + "global index": "GeoBench_30", + "flip": 0 + }, + { + "global index": "GeoBench_502", + "flip": 1 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 1 + }, + { + "global index": "GeoBench_766", + "flip": 1 + }, + { + "global index": "GeoBench_87", + "flip": 1 + }, + { + "global index": "GeoBench_915", + "flip": 1 + }, + { + "global index": "GeoBench_944", + "flip": 0 + }, + { + "global index": "GeoBench_968", + "flip": 1 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 0 + }, + { + "global index": "LiveCodeBench_105", + "flip": 0 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 1 + }, + { + "global index": "LiveCodeBench_131", + "flip": 1 + }, + { + "global index": "LiveCodeBench_136", + "flip": 1 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 1 + }, + { + "global index": "LiveCodeBench_271", + "flip": 1 + }, + { + "global index": "LiveCodeBench_350", + "flip": 1 + }, + { + "global index": "LiveCodeBench_386", + "flip": 1 + }, + { + "global index": "LiveCodeBench_405", + "flip": 1 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 0 + }, + { + "global index": "LiveCodeBench_437", + "flip": 1 + }, + { + "global index": "LiveCodeBench_476", + "flip": 1 + }, + { + "global index": "LiveCodeBench_485", + "flip": 1 + }, + { + "global index": "LiveCodeBench_49", + "flip": 0 + }, + { + "global index": "LiveCodeBench_491", + "flip": 0 + }, + { + "global index": "LiveCodeBench_499", + "flip": 1 + }, + { + "global index": "MATH_108", + "flip": 1 + }, + { + "global index": "MATH_442", + "flip": 0 + }, + { + "global index": "MATH_53", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 1 + }, + { + "global index": "MMLUPro_business_226", + "flip": 0 + }, + { + "global index": "MMLUPro_business_294", + "flip": 0 + }, + { + "global index": "MMLUPro_business_378", + "flip": 0 + }, + { + "global index": "MMLUPro_business_430", + "flip": 1 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 0 + }, + { + "global index": "MMLUPro_business_6", + "flip": 0 + }, + { + "global index": "MMLUPro_business_784", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 1 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 1 + }, + { + "global index": "MMLUPro_law_806", + "flip": 0 + }, + { + "global index": "MMLUPro_law_899", + "flip": 1 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 1 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 1 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 1 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 1 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 1 + }, + { + "global index": "MMLU_management_41", + "flip": 0 + }, + { + "global index": "MMLU_management_77", + "flip": 1 + }, + { + "global index": "MMLU_management_91", + "flip": 1 + }, + { + "global index": "MMLU_management_93", + "flip": 0 + }, + { + "global index": "MathQA_158", + "flip": 0 + }, + { + "global index": "MathQA_1742", + "flip": 0 + }, + { + "global index": "MathQA_202", + "flip": 0 + }, + { + "global index": "MathQA_2092", + "flip": 1 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 1 + }, + { + "global index": "MathQA_84", + "flip": 0 + }, + { + "global index": "MedMCQA_1005", + "flip": 1 + }, + { + "global index": "MedMCQA_1054", + "flip": 1 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 1 + }, + { + "global index": "MedMCQA_1362", + "flip": 0 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 1 + }, + { + "global index": "MedMCQA_2323", + "flip": 0 + }, + { + "global index": "MedMCQA_2366", + "flip": 0 + }, + { + "global index": "MedMCQA_2581", + "flip": 0 + }, + { + "global index": "MedMCQA_511", + "flip": 0 + }, + { + "global index": "MedMCQA_59", + "flip": 1 + }, + { + "global index": "MedMCQA_643", + "flip": 0 + }, + { + "global index": "MedMCQA_853", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 1 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 1 + }, + { + "global index": "NarrativeQA_1683", + "flip": 0 + }, + { + "global index": "NarrativeQA_2474", + "flip": 1 + }, + { + "global index": "NarrativeQA_2820", + "flip": 0 + }, + { + "global index": "NarrativeQA_3282", + "flip": 1 + }, + { + "global index": "NarrativeQA_4102", + "flip": 1 + }, + { + "global index": "NarrativeQA_4128", + "flip": 0 + }, + { + "global index": "NarrativeQA_4347", + "flip": 0 + }, + { + "global index": "NarrativeQA_4540", + "flip": 1 + }, + { + "global index": "NarrativeQA_5022", + "flip": 1 + }, + { + "global index": "NarrativeQA_5259", + "flip": 1 + }, + { + "global index": "NarrativeQA_533", + "flip": 0 + }, + { + "global index": "NarrativeQA_5894", + "flip": 0 + }, + { + "global index": "NarrativeQA_6829", + "flip": 0 + }, + { + "global index": "NarrativeQA_7678", + "flip": 1 + }, + { + "global index": "NarrativeQA_7964", + "flip": 0 + }, + { + "global index": "NarrativeQA_8215", + "flip": 1 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 1 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 1 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 1 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 1 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 1 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 1 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 1 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 1 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 1 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 1 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 0 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 1 + }, + { + "global index": "PubMedQA_0", + "flip": 0 + }, + { + "global index": "PubMedQA_154", + "flip": 0 + }, + { + "global index": "PubMedQA_18", + "flip": 1 + }, + { + "global index": "PubMedQA_238", + "flip": 1 + }, + { + "global index": "PubMedQA_250", + "flip": 0 + }, + { + "global index": "PubMedQA_337", + "flip": 0 + }, + { + "global index": "PubMedQA_362", + "flip": 1 + }, + { + "global index": "PubMedQA_437", + "flip": 1 + }, + { + "global index": "PubMedQA_510", + "flip": 1 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 1 + }, + { + "global index": "PubMedQA_582", + "flip": 0 + }, + { + "global index": "PubMedQA_588", + "flip": 1 + }, + { + "global index": "PubMedQA_610", + "flip": 1 + }, + { + "global index": "PubMedQA_63", + "flip": 1 + }, + { + "global index": "PubMedQA_643", + "flip": 1 + }, + { + "global index": "PubMedQA_687", + "flip": 1 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 1 + }, + { + "global index": "PubMedQA_755", + "flip": 0 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 0 + }, + { + "global index": "PubMedQA_854", + "flip": 0 + }, + { + "global index": "PubMedQA_905", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 1 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 1 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 1 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 1 + }, + { + "global index": "QANTA_Geography_304", + "flip": 1 + }, + { + "global index": "QANTA_History_1084", + "flip": 1 + }, + { + "global index": "QANTA_History_1154", + "flip": 0 + }, + { + "global index": "QANTA_History_433", + "flip": 1 + }, + { + "global index": "QANTA_History_473", + "flip": 1 + }, + { + "global index": "QANTA_History_926", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 1 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 1 + }, + { + "global index": "QANTA_Literature_386", + "flip": 0 + }, + { + "global index": "QANTA_Literature_408", + "flip": 1 + }, + { + "global index": "QANTA_Literature_475", + "flip": 0 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 1 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 1 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 1 + }, + { + "global index": "QANTA_Science_1360", + "flip": 0 + }, + { + "global index": "QANTA_Science_1473", + "flip": 0 + }, + { + "global index": "QANTA_Science_308", + "flip": 1 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 1 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 0 + }, + { + "global index": "SocialiQA_13810", + "flip": 1 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 1 + }, + { + "global index": "SocialiQA_7839", + "flip": 0 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 1 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 1 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 1 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 1 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 1 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 1 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 0 + }, + { + "global index": "WMT19-de-en_46", + "flip": 1 + }, + { + "global index": "WMT19-de-en_715", + "flip": 0 + }, + { + "global index": "WMT19-de-en_883", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 1 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 1 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 1 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 1 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 0 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 1 + } +] \ No newline at end of file diff --git a/src/data/flip_labels/flip_labels_routerDC.json b/src/data/flip_labels/flip_labels_routerDC.json new file mode 100644 index 0000000..d46f448 --- /dev/null +++ b/src/data/flip_labels/flip_labels_routerDC.json @@ -0,0 +1,1682 @@ +[ + { + "global index": "AIME_112", + "flip": 1 + }, + { + "global index": "AIME_58", + "flip": 0 + }, + { + "global index": "ArcMMLU_12", + "flip": 0 + }, + { + "global index": "ArcMMLU_123", + "flip": 0 + }, + { + "global index": "ArcMMLU_16", + "flip": 0 + }, + { + "global index": "ArcMMLU_182", + "flip": 0 + }, + { + "global index": "ArcMMLU_230", + "flip": 0 + }, + { + "global index": "ArcMMLU_293", + "flip": 0 + }, + { + "global index": "ArcMMLU_349", + "flip": 0 + }, + { + "global index": "ArcMMLU_378", + "flip": 0 + }, + { + "global index": "ArcMMLU_443", + "flip": 0 + }, + { + "global index": "ArcMMLU_496", + "flip": 0 + }, + { + "global index": "ArcMMLU_631", + "flip": 0 + }, + { + "global index": "ArcMMLU_646", + "flip": 0 + }, + { + "global index": "ArcMMLU_659", + "flip": 0 + }, + { + "global index": "ArcMMLU_676", + "flip": 0 + }, + { + "global index": "ArcMMLU_685", + "flip": 0 + }, + { + "global index": "ArcMMLU_689", + "flip": 0 + }, + { + "global index": "ArcMMLU_702", + "flip": 0 + }, + { + "global index": "ArcMMLU_713", + "flip": 0 + }, + { + "global index": "ArcMMLU_98", + "flip": 0 + }, + { + "global index": "AsDiv_1165", + "flip": 1 + }, + { + "global index": "AsDiv_1347", + "flip": 0 + }, + { + "global index": "AsDiv_472", + "flip": 0 + }, + { + "global index": "AsDiv_733", + "flip": 0 + }, + { + "global index": "ChessInstruct_0", + "flip": 0 + }, + { + "global index": "ChessInstruct_107", + "flip": 0 + }, + { + "global index": "ChessInstruct_144", + "flip": 1 + }, + { + "global index": "ChessInstruct_42", + "flip": 0 + }, + { + "global index": "ChessInstruct_58", + "flip": 0 + }, + { + "global index": "ChessInstruct_71", + "flip": 0 + }, + { + "global index": "ChessInstruct_84", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_28", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_51", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_6", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_62", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_70", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_85", + "flip": 0 + }, + { + "global index": "Ethics_commonsense_90", + "flip": 1 + }, + { + "global index": "Ethics_deontology_0", + "flip": 0 + }, + { + "global index": "Ethics_deontology_2", + "flip": 0 + }, + { + "global index": "Ethics_deontology_31", + "flip": 0 + }, + { + "global index": "Ethics_deontology_32", + "flip": 0 + }, + { + "global index": "Ethics_deontology_56", + "flip": 0 + }, + { + "global index": "Ethics_justice_1", + "flip": 0 + }, + { + "global index": "Ethics_justice_45", + "flip": 0 + }, + { + "global index": "Ethics_justice_76", + "flip": 0 + }, + { + "global index": "Ethics_justice_84", + "flip": 0 + }, + { + "global index": "Ethics_virtue_14", + "flip": 0 + }, + { + "global index": "Ethics_virtue_26", + "flip": 1 + }, + { + "global index": "Ethics_virtue_30", + "flip": 0 + }, + { + "global index": "Ethics_virtue_48", + "flip": 0 + }, + { + "global index": "Ethics_virtue_51", + "flip": 0 + }, + { + "global index": "FinQA_149", + "flip": 1 + }, + { + "global index": "FinQA_208", + "flip": 0 + }, + { + "global index": "FinQA_56", + "flip": 1 + }, + { + "global index": "FinQA_60", + "flip": 0 + }, + { + "global index": "GSM8K_43", + "flip": 0 + }, + { + "global index": "GeoBench_1002", + "flip": 0 + }, + { + "global index": "GeoBench_1094", + "flip": 0 + }, + { + "global index": "GeoBench_1102", + "flip": 0 + }, + { + "global index": "GeoBench_1113", + "flip": 0 + }, + { + "global index": "GeoBench_124", + "flip": 0 + }, + { + "global index": "GeoBench_1243", + "flip": 0 + }, + { + "global index": "GeoBench_30", + "flip": 0 + }, + { + "global index": "GeoBench_502", + "flip": 0 + }, + { + "global index": "GeoBench_526", + "flip": 0 + }, + { + "global index": "GeoBench_591", + "flip": 0 + }, + { + "global index": "GeoBench_766", + "flip": 0 + }, + { + "global index": "GeoBench_87", + "flip": 0 + }, + { + "global index": "GeoBench_915", + "flip": 0 + }, + { + "global index": "GeoBench_944", + "flip": 0 + }, + { + "global index": "GeoBench_968", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_27", + "flip": 0 + }, + { + "global index": "GeoGraphyData_100k_42", + "flip": 0 + }, + { + "global index": "LiveCodeBench_105", + "flip": 0 + }, + { + "global index": "LiveCodeBench_114", + "flip": 0 + }, + { + "global index": "LiveCodeBench_118", + "flip": 0 + }, + { + "global index": "LiveCodeBench_131", + "flip": 1 + }, + { + "global index": "LiveCodeBench_136", + "flip": 0 + }, + { + "global index": "LiveCodeBench_181", + "flip": 0 + }, + { + "global index": "LiveCodeBench_237", + "flip": 0 + }, + { + "global index": "LiveCodeBench_271", + "flip": 1 + }, + { + "global index": "LiveCodeBench_350", + "flip": 0 + }, + { + "global index": "LiveCodeBench_386", + "flip": 0 + }, + { + "global index": "LiveCodeBench_405", + "flip": 0 + }, + { + "global index": "LiveCodeBench_43", + "flip": 0 + }, + { + "global index": "LiveCodeBench_431", + "flip": 1 + }, + { + "global index": "LiveCodeBench_437", + "flip": 0 + }, + { + "global index": "LiveCodeBench_476", + "flip": 1 + }, + { + "global index": "LiveCodeBench_485", + "flip": 0 + }, + { + "global index": "LiveCodeBench_49", + "flip": 0 + }, + { + "global index": "LiveCodeBench_491", + "flip": 0 + }, + { + "global index": "LiveCodeBench_499", + "flip": 0 + }, + { + "global index": "MATH_108", + "flip": 0 + }, + { + "global index": "MATH_442", + "flip": 0 + }, + { + "global index": "MATH_53", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2808", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2912", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2980", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_2985", + "flip": 0 + }, + { + "global index": "MMLUPro_biology_3188", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3215", + "flip": 1 + }, + { + "global index": "MMLUPro_biology_3225", + "flip": 0 + }, + { + "global index": "MMLUPro_business_226", + "flip": 0 + }, + { + "global index": "MMLUPro_business_294", + "flip": 0 + }, + { + "global index": "MMLUPro_business_378", + "flip": 0 + }, + { + "global index": "MMLUPro_business_430", + "flip": 0 + }, + { + "global index": "MMLUPro_business_503", + "flip": 0 + }, + { + "global index": "MMLUPro_business_507", + "flip": 0 + }, + { + "global index": "MMLUPro_business_6", + "flip": 1 + }, + { + "global index": "MMLUPro_business_784", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3796", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_3837", + "flip": 1 + }, + { + "global index": "MMLUPro_chemistry_3974", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4067", + "flip": 0 + }, + { + "global index": "MMLUPro_chemistry_4407", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9086", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9110", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9136", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9138", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9149", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9200", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9212", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9239", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9264", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9285", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9289", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9414", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9415", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9430", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9452", + "flip": 0 + }, + { + "global index": "MMLUPro_computer science_9471", + "flip": 1 + }, + { + "global index": "MMLUPro_computer science_9475", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5769", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5907", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_5931", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_5965", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6114", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6122", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6135", + "flip": 1 + }, + { + "global index": "MMLUPro_economics_6325", + "flip": 0 + }, + { + "global index": "MMLUPro_economics_6353", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10076", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10125", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10179", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10195", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10199", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10298", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10342", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10395", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10428", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10432", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10473", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10537", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10701", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10823", + "flip": 0 + }, + { + "global index": "MMLUPro_engineering_10864", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4885", + "flip": 0 + }, + { + "global index": "MMLUPro_health_4973", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5093", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5144", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5214", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5215", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5261", + "flip": 0 + }, + { + "global index": "MMLUPro_health_5473", + "flip": 1 + }, + { + "global index": "MMLUPro_health_5514", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4486", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4490", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4497", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4509", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4517", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4523", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4605", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4629", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4638", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4717", + "flip": 1 + }, + { + "global index": "MMLUPro_history_4749", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4752", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4774", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4810", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4833", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4836", + "flip": 0 + }, + { + "global index": "MMLUPro_history_4841", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1007", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1031", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1386", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1462", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1484", + "flip": 0 + }, + { + "global index": "MMLUPro_law_1518", + "flip": 1 + }, + { + "global index": "MMLUPro_law_1818", + "flip": 0 + }, + { + "global index": "MMLUPro_law_806", + "flip": 1 + }, + { + "global index": "MMLUPro_law_899", + "flip": 1 + }, + { + "global index": "MMLUPro_math_6429", + "flip": 1 + }, + { + "global index": "MMLUPro_math_6526", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6623", + "flip": 0 + }, + { + "global index": "MMLUPro_math_6848", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7101", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7249", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7284", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7451", + "flip": 0 + }, + { + "global index": "MMLUPro_math_7577", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9510", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9536", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9663", + "flip": 1 + }, + { + "global index": "MMLUPro_philosophy_9672", + "flip": 0 + }, + { + "global index": "MMLUPro_philosophy_9943", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7773", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7887", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_7893", + "flip": 1 + }, + { + "global index": "MMLUPro_physics_8888", + "flip": 0 + }, + { + "global index": "MMLUPro_physics_9017", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2005", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2186", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2329", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2406", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2420", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2450", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2457", + "flip": 0 + }, + { + "global index": "MMLUPro_psychology_2524", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_121", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_16", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_32", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_63", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_7", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_70", + "flip": 0 + }, + { + "global index": "MMLU_formal_logic_85", + "flip": 0 + }, + { + "global index": "MMLU_management_4", + "flip": 0 + }, + { + "global index": "MMLU_management_41", + "flip": 0 + }, + { + "global index": "MMLU_management_77", + "flip": 0 + }, + { + "global index": "MMLU_management_91", + "flip": 0 + }, + { + "global index": "MMLU_management_93", + "flip": 0 + }, + { + "global index": "MathQA_158", + "flip": 0 + }, + { + "global index": "MathQA_1742", + "flip": 0 + }, + { + "global index": "MathQA_202", + "flip": 0 + }, + { + "global index": "MathQA_2092", + "flip": 0 + }, + { + "global index": "MathQA_2102", + "flip": 0 + }, + { + "global index": "MathQA_2851", + "flip": 0 + }, + { + "global index": "MathQA_827", + "flip": 0 + }, + { + "global index": "MathQA_84", + "flip": 0 + }, + { + "global index": "MedMCQA_1005", + "flip": 0 + }, + { + "global index": "MedMCQA_1054", + "flip": 0 + }, + { + "global index": "MedMCQA_1298", + "flip": 0 + }, + { + "global index": "MedMCQA_1309", + "flip": 0 + }, + { + "global index": "MedMCQA_1362", + "flip": 0 + }, + { + "global index": "MedMCQA_145", + "flip": 0 + }, + { + "global index": "MedMCQA_2010", + "flip": 0 + }, + { + "global index": "MedMCQA_2323", + "flip": 0 + }, + { + "global index": "MedMCQA_2366", + "flip": 0 + }, + { + "global index": "MedMCQA_2581", + "flip": 0 + }, + { + "global index": "MedMCQA_511", + "flip": 0 + }, + { + "global index": "MedMCQA_59", + "flip": 0 + }, + { + "global index": "MedMCQA_643", + "flip": 0 + }, + { + "global index": "MedMCQA_853", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_126", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_14", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_147", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_152", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_188", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_189", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_240", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_33", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_337", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_340", + "flip": 0 + }, + { + "global index": "MusicTheoryBench_70", + "flip": 0 + }, + { + "global index": "NarrativeQA_131", + "flip": 0 + }, + { + "global index": "NarrativeQA_1683", + "flip": 0 + }, + { + "global index": "NarrativeQA_2474", + "flip": 0 + }, + { + "global index": "NarrativeQA_2820", + "flip": 0 + }, + { + "global index": "NarrativeQA_3282", + "flip": 0 + }, + { + "global index": "NarrativeQA_4102", + "flip": 1 + }, + { + "global index": "NarrativeQA_4128", + "flip": 1 + }, + { + "global index": "NarrativeQA_4347", + "flip": 0 + }, + { + "global index": "NarrativeQA_4540", + "flip": 0 + }, + { + "global index": "NarrativeQA_5022", + "flip": 1 + }, + { + "global index": "NarrativeQA_5259", + "flip": 0 + }, + { + "global index": "NarrativeQA_533", + "flip": 1 + }, + { + "global index": "NarrativeQA_5894", + "flip": 1 + }, + { + "global index": "NarrativeQA_6829", + "flip": 0 + }, + { + "global index": "NarrativeQA_7678", + "flip": 1 + }, + { + "global index": "NarrativeQA_7964", + "flip": 1 + }, + { + "global index": "NarrativeQA_8215", + "flip": 0 + }, + { + "global index": "NarrativeQA_8598", + "flip": 0 + }, + { + "global index": "NarrativeQA_927", + "flip": 1 + }, + { + "global index": "OpenTDB_Animals_2545", + "flip": 0 + }, + { + "global index": "OpenTDB_Animals_262", + "flip": 0 + }, + { + "global index": "OpenTDB_Art_1429", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1078", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_1456", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3577", + "flip": 0 + }, + { + "global index": "OpenTDB_Celebrities_3968", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1178", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1807", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_1957", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_2181", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3404", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_3727", + "flip": 0 + }, + { + "global index": "OpenTDB_General Knowledge_4019", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2099", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_2346", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_3880", + "flip": 0 + }, + { + "global index": "OpenTDB_Geography_792", + "flip": 0 + }, + { + "global index": "OpenTDB_History_1162", + "flip": 0 + }, + { + "global index": "OpenTDB_History_2026", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3712", + "flip": 0 + }, + { + "global index": "OpenTDB_History_3902", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1175", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_1560", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_3716", + "flip": 0 + }, + { + "global index": "OpenTDB_Science & Nature_476", + "flip": 0 + }, + { + "global index": "OpenTDB_Sports_2289", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1173", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_1419", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_2519", + "flip": 0 + }, + { + "global index": "OpenTDB_Vehicles_3234", + "flip": 0 + }, + { + "global index": "PubMedQA_0", + "flip": 0 + }, + { + "global index": "PubMedQA_154", + "flip": 1 + }, + { + "global index": "PubMedQA_18", + "flip": 0 + }, + { + "global index": "PubMedQA_238", + "flip": 1 + }, + { + "global index": "PubMedQA_250", + "flip": 1 + }, + { + "global index": "PubMedQA_337", + "flip": 1 + }, + { + "global index": "PubMedQA_362", + "flip": 1 + }, + { + "global index": "PubMedQA_437", + "flip": 1 + }, + { + "global index": "PubMedQA_510", + "flip": 0 + }, + { + "global index": "PubMedQA_520", + "flip": 0 + }, + { + "global index": "PubMedQA_575", + "flip": 1 + }, + { + "global index": "PubMedQA_582", + "flip": 1 + }, + { + "global index": "PubMedQA_588", + "flip": 0 + }, + { + "global index": "PubMedQA_610", + "flip": 0 + }, + { + "global index": "PubMedQA_63", + "flip": 1 + }, + { + "global index": "PubMedQA_643", + "flip": 0 + }, + { + "global index": "PubMedQA_687", + "flip": 1 + }, + { + "global index": "PubMedQA_722", + "flip": 0 + }, + { + "global index": "PubMedQA_73", + "flip": 1 + }, + { + "global index": "PubMedQA_755", + "flip": 0 + }, + { + "global index": "PubMedQA_8", + "flip": 0 + }, + { + "global index": "PubMedQA_81", + "flip": 0 + }, + { + "global index": "PubMedQA_854", + "flip": 1 + }, + { + "global index": "PubMedQA_905", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1212", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_1702", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_828", + "flip": 0 + }, + { + "global index": "QANTA_Fine Arts_865", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1023", + "flip": 0 + }, + { + "global index": "QANTA_Geography_1555", + "flip": 0 + }, + { + "global index": "QANTA_Geography_304", + "flip": 0 + }, + { + "global index": "QANTA_History_1084", + "flip": 0 + }, + { + "global index": "QANTA_History_1154", + "flip": 0 + }, + { + "global index": "QANTA_History_433", + "flip": 0 + }, + { + "global index": "QANTA_History_473", + "flip": 0 + }, + { + "global index": "QANTA_History_926", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1045", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1073", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1239", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1326", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1727", + "flip": 0 + }, + { + "global index": "QANTA_Literature_1843", + "flip": 0 + }, + { + "global index": "QANTA_Literature_386", + "flip": 0 + }, + { + "global index": "QANTA_Literature_408", + "flip": 0 + }, + { + "global index": "QANTA_Literature_475", + "flip": 0 + }, + { + "global index": "QANTA_Literature_833", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_1270", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_499", + "flip": 0 + }, + { + "global index": "QANTA_Philosophy_91", + "flip": 0 + }, + { + "global index": "QANTA_Science_1360", + "flip": 0 + }, + { + "global index": "QANTA_Science_1473", + "flip": 0 + }, + { + "global index": "QANTA_Science_308", + "flip": 0 + }, + { + "global index": "QANTA_Science_619", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_1847", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_2", + "flip": 0 + }, + { + "global index": "QANTA_Social Science_77", + "flip": 0 + }, + { + "global index": "SocialiQA_13810", + "flip": 0 + }, + { + "global index": "SocialiQA_22095", + "flip": 0 + }, + { + "global index": "SocialiQA_26846", + "flip": 0 + }, + { + "global index": "SocialiQA_7839", + "flip": 0 + }, + { + "global index": "SuperGLUE-CausalReasoning_4526", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_12894", + "flip": 0 + }, + { + "global index": "SuperGLUE-ClozeTest_17965", + "flip": 1 + }, + { + "global index": "SuperGLUE-ClozeTest_18766", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19410", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_19567", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_522", + "flip": 0 + }, + { + "global index": "SuperGLUE-Entailment_767", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_1408", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_3137", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4046", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4102", + "flip": 0 + }, + { + "global index": "SuperGLUE-QA_4160", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7725", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_7738", + "flip": 0 + }, + { + "global index": "SuperGLUE-RC_8531", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19695", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_19738", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20079", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20189", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wic_20253", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20368", + "flip": 0 + }, + { + "global index": "SuperGLUE-Wsc_20370", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_156", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_246", + "flip": 0 + }, + { + "global index": "WMT19-cs-en_568", + "flip": 1 + }, + { + "global index": "WMT19-de-en_46", + "flip": 0 + }, + { + "global index": "WMT19-de-en_715", + "flip": 1 + }, + { + "global index": "WMT19-de-en_883", + "flip": 1 + }, + { + "global index": "WMT19-fi-en_222", + "flip": 0 + }, + { + "global index": "WMT19-fi-en_610", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_116", + "flip": 1 + }, + { + "global index": "WMT19-gu-en_123", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_191", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_491", + "flip": 0 + }, + { + "global index": "WMT19-gu-en_968", + "flip": 0 + }, + { + "global index": "WMT19-kk-en_528", + "flip": 1 + }, + { + "global index": "WMT19-kk-en_826", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_135", + "flip": 1 + }, + { + "global index": "WMT19-lt-en_269", + "flip": 0 + }, + { + "global index": "WMT19-lt-en_636", + "flip": 0 + }, + { + "global index": "WMT19-ru-en_222", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_218", + "flip": 0 + }, + { + "global index": "WMT19-zh-en_252", + "flip": 1 + }, + { + "global index": "WMT19-zh-en_59", + "flip": 0 + } +] \ No newline at end of file From e205155305ea794c24ed5a9645eec9f3b323c3e7 Mon Sep 17 00:00:00 2001 From: Riksin Date: Thu, 18 Dec 2025 07:40:24 -0600 Subject: [PATCH 2/2] Fix pre-commit error --- src/data/flip_labels/flip_labels_CARROT.json | 2 +- src/data/flip_labels/flip_labels_kmeans.json | 2 +- src/data/flip_labels/flip_labels_knn.json | 2 +- src/data/flip_labels/flip_labels_mirt.json | 2 +- src/data/flip_labels/flip_labels_mlp.json | 2 +- src/data/flip_labels/flip_labels_nirt.json | 2 +- src/data/flip_labels/flip_labels_routerDC.json | 2 +- 7 files changed, 7 insertions(+), 7 deletions(-) diff --git a/src/data/flip_labels/flip_labels_CARROT.json b/src/data/flip_labels/flip_labels_CARROT.json index 2fbe639..d3553d7 100644 --- a/src/data/flip_labels/flip_labels_CARROT.json +++ b/src/data/flip_labels/flip_labels_CARROT.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 1 } -] \ No newline at end of file +] diff --git a/src/data/flip_labels/flip_labels_kmeans.json b/src/data/flip_labels/flip_labels_kmeans.json index 56df69e..3f4ea61 100644 --- a/src/data/flip_labels/flip_labels_kmeans.json +++ b/src/data/flip_labels/flip_labels_kmeans.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 0 } -] \ No newline at end of file +] diff --git a/src/data/flip_labels/flip_labels_knn.json b/src/data/flip_labels/flip_labels_knn.json index b6fbe11..fa42e85 100644 --- a/src/data/flip_labels/flip_labels_knn.json +++ b/src/data/flip_labels/flip_labels_knn.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 0 } -] \ No newline at end of file +] diff --git a/src/data/flip_labels/flip_labels_mirt.json b/src/data/flip_labels/flip_labels_mirt.json index a17bb28..6eb145e 100644 --- a/src/data/flip_labels/flip_labels_mirt.json +++ b/src/data/flip_labels/flip_labels_mirt.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 0 } -] \ No newline at end of file +] diff --git a/src/data/flip_labels/flip_labels_mlp.json b/src/data/flip_labels/flip_labels_mlp.json index 5f59f9f..c3c6fb0 100644 --- a/src/data/flip_labels/flip_labels_mlp.json +++ b/src/data/flip_labels/flip_labels_mlp.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 0 } -] \ No newline at end of file +] diff --git a/src/data/flip_labels/flip_labels_nirt.json b/src/data/flip_labels/flip_labels_nirt.json index 2b258a5..911a85c 100644 --- a/src/data/flip_labels/flip_labels_nirt.json +++ b/src/data/flip_labels/flip_labels_nirt.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 1 } -] \ No newline at end of file +] diff --git a/src/data/flip_labels/flip_labels_routerDC.json b/src/data/flip_labels/flip_labels_routerDC.json index d46f448..2edf41e 100644 --- a/src/data/flip_labels/flip_labels_routerDC.json +++ b/src/data/flip_labels/flip_labels_routerDC.json @@ -1679,4 +1679,4 @@ "global index": "WMT19-zh-en_59", "flip": 0 } -] \ No newline at end of file +]