Ctrl+K
- arc_challenge_global_ridge_N12
- arc_challenge_global_ridge_N16
- arc_challenge_global_ridge_N5
- arc_challenge_mean_N16
- arc_challenge_pertensor_mlp_N16
- arc_challenge_pertensor_pca_N16
- arc_challenge_pertensor_ridge_N16
- arc_challenge_procrustes_N16
- arc_challenge_topk12_global_ridge_N12
- arc_challenge_topk12_global_ridge_N16
- arc_challenge_topk8_global_ridge_N12
- arc_challenge_topk8_global_ridge_N16
- arc_challenge_topk8_global_ridge_all_N16
- arc_challenge_topk8_global_ridge_code-only_N3
- arc_challenge_topk8_global_ridge_math+code_N9
- arc_challenge_topk8_global_ridge_math-only_N6
- arc_challenge_topk8_global_ridge_science-only_N7
- arc_challenge_topk8_pertensor_ridge_N16
- gsm8k_test_500_global_ridge_N12
- gsm8k_test_500_global_ridge_N16
- gsm8k_test_500_global_ridge_N5
- gsm8k_test_500_mean_N16
- gsm8k_test_500_pertensor_mlp_N16
- gsm8k_test_500_pertensor_pca_N16
- gsm8k_test_500_pertensor_ridge_N16
- gsm8k_test_500_procrustes_N16
- gsm8k_test_500_topk12_global_ridge_N12
- gsm8k_test_500_topk12_global_ridge_N16
- gsm8k_test_500_topk8_global_ridge_N12
- gsm8k_test_500_topk8_global_ridge_N16
- gsm8k_test_500_topk8_global_ridge_all_N16
- gsm8k_test_500_topk8_global_ridge_code-only_N3
- gsm8k_test_500_topk8_global_ridge_math+code_N9
- gsm8k_test_500_topk8_global_ridge_math-only_N6
- gsm8k_test_500_topk8_global_ridge_science-only_N7
- gsm8k_test_500_topk8_pertensor_ridge_N16
- gsm_hard_global_ridge_N12
- gsm_hard_global_ridge_N16
- gsm_hard_global_ridge_N5
- gsm_hard_mean_N16
- gsm_hard_pertensor_mlp_N16
- gsm_hard_pertensor_pca_N16
- gsm_hard_pertensor_ridge_N16
- gsm_hard_procrustes_N16
- gsm_hard_topk12_global_ridge_N12
- gsm_hard_topk12_global_ridge_N16
- gsm_hard_topk8_global_ridge_N12
- gsm_hard_topk8_global_ridge_N16
- gsm_hard_topk8_global_ridge_all_N16
- gsm_hard_topk8_global_ridge_code-only_N3