{ "n_pairs": 1000, "pairwise_accuracy": 0.713, "mean_margin": 1.0103333097100258, "ci_low": 0.685975, "ci_high": 0.741, "ece": 0.02271926368486851, "per_subset": { "regular": { "n_pairs": 400, "accuracy": 0.74 }, "expressive": { "n_pairs": 600, "accuracy": 0.695 } }, "per_language": { "zh2en": { "n_pairs": 148, "accuracy": 0.6621621621621622 }, "en2en": { "n_pairs": 252, "accuracy": 0.6388888888888888 }, "zh2zh": { "n_pairs": 179, "accuracy": 0.8324022346368715 }, "en2zh": { "n_pairs": 221, "accuracy": 0.8733031674208145 }, "en2mixed": { "n_pairs": 120, "accuracy": 0.525 }, "zh2mixed": { "n_pairs": 80, "accuracy": 0.6125 } }, "run_name": "natscore-small-v0-kaggle / dev[:1000]", "ablation_config": "(headline)" }