diff --git a/data.json b/data.json index 4d8a10a..a9a2fea 100644 --- a/data.json +++ b/data.json @@ -1719,10 +1719,10 @@ "dataset": "AESLC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.6, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -1743,10 +1743,10 @@ "dataset": "AESLC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 45.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -1767,10 +1767,10 @@ "dataset": "Amazon-Reviews", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.3, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -1779,10 +1779,10 @@ "dataset": "Amazon-Reviews", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -1791,10 +1791,10 @@ "dataset": "Amazon-Reviews", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -1803,10 +1803,10 @@ "dataset": "Amazon-Reviews", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2079,10 +2079,10 @@ "dataset": "eSNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2091,10 +2091,10 @@ "dataset": "eSNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2127,10 +2127,10 @@ "dataset": "Gigaword", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2139,10 +2139,10 @@ "dataset": "Gigaword", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.8, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2151,10 +2151,10 @@ "dataset": "AX", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2163,10 +2163,10 @@ "dataset": "AX", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.4, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2175,10 +2175,10 @@ "dataset": "AX", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 5.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2187,10 +2187,10 @@ "dataset": "AX", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 6.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2198,10 +2198,10 @@ "model": "C4", "dataset": "MNLI-m", "train_split": null, - "dev_split": "suspicious", + "dev_split": "contaminated", "test_split": "n/a", "train_percent": null, - "dev_percent": null, + "dev_percent": 1.6, "test_percent": null, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" @@ -2210,10 +2210,10 @@ "model": "OSCAR", "dataset": "MNLI-m", "train_split": null, - "dev_split": "suspicious", + "dev_split": "contaminated", "test_split": "n/a", "train_percent": null, - "dev_percent": null, + "dev_percent": 1.8, "test_percent": null, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" @@ -2222,10 +2222,10 @@ "model": "ThePile", "dataset": "MNLI-m", "train_split": null, - "dev_split": "suspicious", + "dev_split": "contaminated", "test_split": "n/a", "train_percent": null, - "dev_percent": null, + "dev_percent": 2.2, "test_percent": null, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" @@ -2234,10 +2234,10 @@ "model": "RedPajama", "dataset": "MNLI-m", "train_split": null, - "dev_split": "suspicious", + "dev_split": "contaminated", "test_split": "n/a", "train_percent": null, - "dev_percent": null, + "dev_percent": 2.3, "test_percent": null, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" @@ -2246,11 +2246,11 @@ "model": "C4", "dataset": "MNLI-mm", "train_split": null, - "dev_split": "suspicious", - "test_split": "n/a", + "dev_split": null, + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.7, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2258,11 +2258,11 @@ "model": "OSCAR", "dataset": "MNLI-mm", "train_split": null, - "dev_split": "suspicious", - "test_split": "n/a", + "dev_split": null, + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2270,11 +2270,11 @@ "model": "ThePile", "dataset": "MNLI-mm", "train_split": null, - "dev_split": "suspicious", - "test_split": "n/a", + "dev_split": null, + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2282,11 +2282,11 @@ "model": "RedPajama", "dataset": "MNLI-mm", "train_split": null, - "dev_split": "suspicious", - "test_split": "n/a", + "dev_split": null, + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2331,10 +2331,10 @@ "dataset": "MRPC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2367,10 +2367,10 @@ "dataset": "QNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2379,10 +2379,10 @@ "dataset": "QNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2415,10 +2415,10 @@ "dataset": "QQP", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2427,10 +2427,10 @@ "dataset": "QQP", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2475,10 +2475,10 @@ "dataset": "RTE", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 67.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2487,10 +2487,10 @@ "dataset": "STSB", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 3.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2499,10 +2499,10 @@ "dataset": "STSB", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 3.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2511,10 +2511,10 @@ "dataset": "STSB", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 11.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2523,10 +2523,10 @@ "dataset": "STSB", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 9.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2559,10 +2559,10 @@ "dataset": "WNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 10.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2571,10 +2571,10 @@ "dataset": "WNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2583,10 +2583,10 @@ "dataset": "HeadQA-en", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 5.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2595,10 +2595,10 @@ "dataset": "HeadQA-en", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 5.3, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2607,10 +2607,10 @@ "dataset": "HeadQA-en", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 5.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2619,10 +2619,10 @@ "dataset": "HeadQA-en", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 5.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2631,10 +2631,10 @@ "dataset": "health-fact", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 7.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2643,10 +2643,10 @@ "dataset": "health-fact", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 3.4, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2655,10 +2655,10 @@ "dataset": "health-fact", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2667,10 +2667,10 @@ "dataset": "health-fact", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 18.7, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2727,10 +2727,10 @@ "dataset": "LIAR", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 29.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2739,10 +2739,10 @@ "dataset": "LIAR", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 13.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2751,10 +2751,10 @@ "dataset": "LIAR", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 10.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2763,10 +2763,10 @@ "dataset": "LIAR", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 45.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -2979,10 +2979,10 @@ "dataset": "HumanEval", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3303,10 +3303,10 @@ "dataset": "SciCite", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.8, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3315,10 +3315,10 @@ "dataset": "SciCite", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3339,10 +3339,10 @@ "dataset": "SciCite", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.7, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3423,10 +3423,10 @@ "dataset": "SemEval-2014", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 4.9, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3435,10 +3435,10 @@ "dataset": "SemEval-2014", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 52.8, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3471,10 +3471,10 @@ "dataset": "SICK", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 4.8, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3483,10 +3483,10 @@ "dataset": "SICK", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 52.6, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3519,10 +3519,10 @@ "dataset": "SNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3531,10 +3531,10 @@ "dataset": "SNLI", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3735,10 +3735,10 @@ "dataset": "Ax-b", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3747,10 +3747,10 @@ "dataset": "Ax-b", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.4, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3759,10 +3759,10 @@ "dataset": "Ax-b", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 5.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3771,10 +3771,10 @@ "dataset": "Ax-b", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 6.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3842,10 +3842,10 @@ "model": "OSCAR", "dataset": "BoolQ", "train_split": null, - "dev_split": "suspicious", + "dev_split": "contaminated", "test_split": "n/a", "train_percent": null, - "dev_percent": null, + "dev_percent": 3.0, "test_percent": null, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" @@ -3903,10 +3903,10 @@ "dataset": "CB", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3915,10 +3915,10 @@ "dataset": "CB", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.6, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3939,10 +3939,10 @@ "dataset": "COPA", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3951,10 +3951,10 @@ "dataset": "COPA", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -3963,10 +3963,10 @@ "dataset": "COPA", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 100.0, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4071,10 +4071,10 @@ "dataset": "WiC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 64.4, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4083,10 +4083,10 @@ "dataset": "WiC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 49.4, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4095,10 +4095,10 @@ "dataset": "WiC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 18.6, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4107,10 +4107,10 @@ "dataset": "WiC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 60.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4119,10 +4119,10 @@ "dataset": "SWAG", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.5, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4131,10 +4131,10 @@ "dataset": "SWAG", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 1.6, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4143,10 +4143,10 @@ "dataset": "SWAG", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4155,10 +4155,10 @@ "dataset": "SWAG", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.8, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4263,10 +4263,10 @@ "dataset": "WSC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 29.3, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4275,10 +4275,10 @@ "dataset": "WSC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 30.4, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4287,10 +4287,10 @@ "dataset": "WSC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 32.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4299,10 +4299,10 @@ "dataset": "WSC", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 58.2, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4407,10 +4407,10 @@ "dataset": "XSum", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 2.1, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4431,10 +4431,10 @@ "dataset": "XSum", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 3.3, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" }, @@ -4443,10 +4443,10 @@ "dataset": "XSum", "train_split": null, "dev_split": null, - "test_split": "suspicious", + "test_split": "contaminated", "train_percent": null, "dev_percent": null, - "test_percent": null, + "test_percent": 4.3, "guidelines": null, "source": "https://arxiv.org/abs/2310.20707" },