run_id	topic_id	metric	value
lg_nt_4q12r3l_mt_c	1001	sentence_support_opt	0.6875
lg_nt_4q12r3l_mt_c	1001	sentence_support_pes	0.6875
lg_nt_4q12r3l_mt_c	1001	sentence_support_llmfilled	0.6875
lg_nt_4q12r3l_mt_c	1001	nugget_mentioned	0.4
lg_nt_4q12r3l_mt_c	1001	nugget_coverage	0.35
lg_nt_4q12r3l_mt_c	1003	sentence_support_opt	0.7333333333333333
lg_nt_4q12r3l_mt_c	1003	sentence_support_pes	0.7333333333333333
lg_nt_4q12r3l_mt_c	1003	sentence_support_llmfilled	0.7333333333333333
lg_nt_4q12r3l_mt_c	1003	nugget_mentioned	0.15
lg_nt_4q12r3l_mt_c	1003	nugget_coverage	0.05
lg_nt_4q12r3l_mt_c	1005	sentence_support_opt	1.0
lg_nt_4q12r3l_mt_c	1005	sentence_support_pes	0.0
lg_nt_4q12r3l_mt_c	1005	sentence_support_llmfilled	0.0
lg_nt_4q12r3l_mt_c	1005	nugget_mentioned	0.25
lg_nt_4q12r3l_mt_c	1005	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1007	sentence_support_opt	0.42857142857142855
lg_nt_4q12r3l_mt_c	1007	sentence_support_pes	0.42857142857142855
lg_nt_4q12r3l_mt_c	1007	sentence_support_llmfilled	0.42857142857142855
lg_nt_4q12r3l_mt_c	1007	nugget_mentioned	0.42105263157894735
lg_nt_4q12r3l_mt_c	1007	nugget_coverage	0.21052631578947367
lg_nt_4q12r3l_mt_c	1009	sentence_support_opt	0.8
lg_nt_4q12r3l_mt_c	1009	sentence_support_pes	0.6
lg_nt_4q12r3l_mt_c	1009	sentence_support_llmfilled	0.6
lg_nt_4q12r3l_mt_c	1009	nugget_mentioned	0.9166666666666666
lg_nt_4q12r3l_mt_c	1009	nugget_coverage	0.5833333333333334
lg_nt_4q12r3l_mt_c	1011	sentence_support_opt	0.8888888888888888
lg_nt_4q12r3l_mt_c	1011	sentence_support_pes	0.8888888888888888
lg_nt_4q12r3l_mt_c	1011	sentence_support_llmfilled	0.8888888888888888
lg_nt_4q12r3l_mt_c	1011	nugget_mentioned	0.47368421052631576
lg_nt_4q12r3l_mt_c	1011	nugget_coverage	0.3684210526315789
lg_nt_4q12r3l_mt_c	1013	sentence_support_opt	0.8
lg_nt_4q12r3l_mt_c	1013	sentence_support_pes	0.4
lg_nt_4q12r3l_mt_c	1013	sentence_support_llmfilled	0.4
lg_nt_4q12r3l_mt_c	1013	nugget_mentioned	0.6875
lg_nt_4q12r3l_mt_c	1013	nugget_coverage	0.3125
lg_nt_4q12r3l_mt_c	1015	sentence_support_opt	0.8125
lg_nt_4q12r3l_mt_c	1015	sentence_support_pes	0.8125
lg_nt_4q12r3l_mt_c	1015	sentence_support_llmfilled	0.8125
lg_nt_4q12r3l_mt_c	1015	nugget_mentioned	0.08333333333333333
lg_nt_4q12r3l_mt_c	1015	nugget_coverage	0.08333333333333333
lg_nt_4q12r3l_mt_c	1017	sentence_support_opt	0.6
lg_nt_4q12r3l_mt_c	1017	sentence_support_pes	0.5333333333333333
lg_nt_4q12r3l_mt_c	1017	sentence_support_llmfilled	0.5333333333333333
lg_nt_4q12r3l_mt_c	1017	nugget_mentioned	0.1
lg_nt_4q12r3l_mt_c	1017	nugget_coverage	0.1
lg_nt_4q12r3l_mt_c	1019	sentence_support_opt	0.9285714285714286
lg_nt_4q12r3l_mt_c	1019	sentence_support_pes	0.21428571428571427
lg_nt_4q12r3l_mt_c	1019	sentence_support_llmfilled	0.21428571428571427
lg_nt_4q12r3l_mt_c	1019	nugget_mentioned	0.4375
lg_nt_4q12r3l_mt_c	1019	nugget_coverage	0.4375
lg_nt_4q12r3l_mt_c	1021	sentence_support_opt	1.0
lg_nt_4q12r3l_mt_c	1021	sentence_support_pes	0.0
lg_nt_4q12r3l_mt_c	1021	sentence_support_llmfilled	0.0
lg_nt_4q12r3l_mt_c	1021	nugget_mentioned	0.35294117647058826
lg_nt_4q12r3l_mt_c	1021	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1023	sentence_support_opt	0.9333333333333333
lg_nt_4q12r3l_mt_c	1023	sentence_support_pes	0.4
lg_nt_4q12r3l_mt_c	1023	sentence_support_llmfilled	0.4
lg_nt_4q12r3l_mt_c	1023	nugget_mentioned	0.2631578947368421
lg_nt_4q12r3l_mt_c	1023	nugget_coverage	0.15789473684210525
lg_nt_4q12r3l_mt_c	1025	sentence_support_opt	0.5714285714285714
lg_nt_4q12r3l_mt_c	1025	sentence_support_pes	0.5
lg_nt_4q12r3l_mt_c	1025	sentence_support_llmfilled	0.5
lg_nt_4q12r3l_mt_c	1025	nugget_mentioned	0.5555555555555556
lg_nt_4q12r3l_mt_c	1025	nugget_coverage	0.5555555555555556
lg_nt_4q12r3l_mt_c	1027	sentence_support_opt	1.0
lg_nt_4q12r3l_mt_c	1027	sentence_support_pes	0.0
lg_nt_4q12r3l_mt_c	1027	sentence_support_llmfilled	0.0
lg_nt_4q12r3l_mt_c	1027	nugget_mentioned	0.25
lg_nt_4q12r3l_mt_c	1027	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1029	sentence_support_opt	0.6666666666666666
lg_nt_4q12r3l_mt_c	1029	sentence_support_pes	0.6
lg_nt_4q12r3l_mt_c	1029	sentence_support_llmfilled	0.6
lg_nt_4q12r3l_mt_c	1029	nugget_mentioned	0.1
lg_nt_4q12r3l_mt_c	1029	nugget_coverage	0.1
lg_nt_4q12r3l_mt_c	1031	sentence_support_opt	0.9375
lg_nt_4q12r3l_mt_c	1031	sentence_support_pes	0.6875
lg_nt_4q12r3l_mt_c	1031	sentence_support_llmfilled	0.6875
lg_nt_4q12r3l_mt_c	1031	nugget_mentioned	0.1
lg_nt_4q12r3l_mt_c	1031	nugget_coverage	0.1
lg_nt_4q12r3l_mt_c	1033	sentence_support_opt	0.7333333333333333
lg_nt_4q12r3l_mt_c	1033	sentence_support_pes	0.6
lg_nt_4q12r3l_mt_c	1033	sentence_support_llmfilled	0.6
lg_nt_4q12r3l_mt_c	1033	nugget_mentioned	0.10526315789473684
lg_nt_4q12r3l_mt_c	1033	nugget_coverage	0.05263157894736842
lg_nt_4q12r3l_mt_c	1035	sentence_support_opt	0.8
lg_nt_4q12r3l_mt_c	1035	sentence_support_pes	0.8
lg_nt_4q12r3l_mt_c	1035	sentence_support_llmfilled	0.8
lg_nt_4q12r3l_mt_c	1035	nugget_mentioned	0.08333333333333333
lg_nt_4q12r3l_mt_c	1035	nugget_coverage	0.08333333333333333
lg_nt_4q12r3l_mt_c	1037	sentence_support_opt	0.38461538461538464
lg_nt_4q12r3l_mt_c	1037	sentence_support_pes	0.38461538461538464
lg_nt_4q12r3l_mt_c	1037	sentence_support_llmfilled	0.38461538461538464
lg_nt_4q12r3l_mt_c	1037	nugget_mentioned	0.13333333333333333
lg_nt_4q12r3l_mt_c	1037	nugget_coverage	0.13333333333333333
lg_nt_4q12r3l_mt_c	1039	sentence_support_opt	1.0
lg_nt_4q12r3l_mt_c	1039	sentence_support_pes	0.0
lg_nt_4q12r3l_mt_c	1039	sentence_support_llmfilled	0.0
lg_nt_4q12r3l_mt_c	1039	nugget_mentioned	0.13333333333333333
lg_nt_4q12r3l_mt_c	1039	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1041	sentence_support_opt	1.0
lg_nt_4q12r3l_mt_c	1041	sentence_support_pes	0.0
lg_nt_4q12r3l_mt_c	1041	sentence_support_llmfilled	0.0
lg_nt_4q12r3l_mt_c	1041	nugget_mentioned	0.2222222222222222
lg_nt_4q12r3l_mt_c	1041	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1047	sentence_support_opt	0.5333333333333333
lg_nt_4q12r3l_mt_c	1047	sentence_support_pes	0.3333333333333333
lg_nt_4q12r3l_mt_c	1047	sentence_support_llmfilled	0.3333333333333333
lg_nt_4q12r3l_mt_c	1047	nugget_mentioned	0.4117647058823529
lg_nt_4q12r3l_mt_c	1047	nugget_coverage	0.17647058823529413
lg_nt_4q12r3l_mt_c	1053	sentence_support_opt	0.8235294117647058
lg_nt_4q12r3l_mt_c	1053	sentence_support_pes	0.35294117647058826
lg_nt_4q12r3l_mt_c	1053	sentence_support_llmfilled	0.35294117647058826
lg_nt_4q12r3l_mt_c	1053	nugget_mentioned	0.3333333333333333
lg_nt_4q12r3l_mt_c	1053	nugget_coverage	0.16666666666666666
lg_nt_4q12r3l_mt_c	1055	sentence_support_opt	0.8823529411764706
lg_nt_4q12r3l_mt_c	1055	sentence_support_pes	0.5882352941176471
lg_nt_4q12r3l_mt_c	1055	sentence_support_llmfilled	0.5882352941176471
lg_nt_4q12r3l_mt_c	1055	nugget_mentioned	0.375
lg_nt_4q12r3l_mt_c	1055	nugget_coverage	0.375
lg_nt_4q12r3l_mt_c	1065	sentence_support_opt	0.7692307692307693
lg_nt_4q12r3l_mt_c	1065	sentence_support_pes	0.23076923076923078
lg_nt_4q12r3l_mt_c	1065	sentence_support_llmfilled	0.23076923076923078
lg_nt_4q12r3l_mt_c	1065	nugget_mentioned	0.1
lg_nt_4q12r3l_mt_c	1065	nugget_coverage	0.05
lg_nt_4q12r3l_mt_c	1067	sentence_support_opt	0.6666666666666666
lg_nt_4q12r3l_mt_c	1067	sentence_support_pes	0.13333333333333333
lg_nt_4q12r3l_mt_c	1067	sentence_support_llmfilled	0.13333333333333333
lg_nt_4q12r3l_mt_c	1067	nugget_mentioned	0.15
lg_nt_4q12r3l_mt_c	1067	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1069	sentence_support_opt	0.8461538461538461
lg_nt_4q12r3l_mt_c	1069	sentence_support_pes	0.3076923076923077
lg_nt_4q12r3l_mt_c	1069	sentence_support_llmfilled	0.3076923076923077
lg_nt_4q12r3l_mt_c	1069	nugget_mentioned	0.0
lg_nt_4q12r3l_mt_c	1069	nugget_coverage	0.0
lg_nt_4q12r3l_mt_c	1075	sentence_support_opt	0.9473684210526315
lg_nt_4q12r3l_mt_c	1075	sentence_support_pes	0.8421052631578947
lg_nt_4q12r3l_mt_c	1075	sentence_support_llmfilled	0.8421052631578947
lg_nt_4q12r3l_mt_c	1075	nugget_mentioned	0.25
lg_nt_4q12r3l_mt_c	1075	nugget_coverage	0.25
lg_nt_4q12r3l_mt_c	1077	sentence_support_opt	0.9444444444444444
lg_nt_4q12r3l_mt_c	1077	sentence_support_pes	0.9444444444444444
lg_nt_4q12r3l_mt_c	1077	sentence_support_llmfilled	0.9444444444444444
lg_nt_4q12r3l_mt_c	1077	nugget_mentioned	0.1
lg_nt_4q12r3l_mt_c	1077	nugget_coverage	0.1
lg_nt_4q12r3l_mt_c	1079	sentence_support_opt	0.8
lg_nt_4q12r3l_mt_c	1079	sentence_support_pes	0.5333333333333333
lg_nt_4q12r3l_mt_c	1079	sentence_support_llmfilled	0.5333333333333333
lg_nt_4q12r3l_mt_c	1079	nugget_mentioned	0.1
lg_nt_4q12r3l_mt_c	1079	nugget_coverage	0.1
lg_nt_4q12r3l_mt_c	1081	sentence_support_opt	1.0
lg_nt_4q12r3l_mt_c	1081	sentence_support_pes	0.7777777777777778
lg_nt_4q12r3l_mt_c	1081	sentence_support_llmfilled	0.7777777777777778
lg_nt_4q12r3l_mt_c	1081	nugget_mentioned	0.5833333333333334
lg_nt_4q12r3l_mt_c	1081	nugget_coverage	0.5833333333333334
lg_nt_4q12r3l_mt_c	1083	sentence_support_opt	0.6470588235294118
lg_nt_4q12r3l_mt_c	1083	sentence_support_pes	0.6470588235294118
lg_nt_4q12r3l_mt_c	1083	sentence_support_llmfilled	0.6470588235294118
lg_nt_4q12r3l_mt_c	1083	nugget_mentioned	0.6363636363636364
lg_nt_4q12r3l_mt_c	1083	nugget_coverage	0.6363636363636364
lg_nt_4q12r3l_mt_c	1085	sentence_support_opt	0.9375
lg_nt_4q12r3l_mt_c	1085	sentence_support_pes	0.875
lg_nt_4q12r3l_mt_c	1085	sentence_support_llmfilled	0.875
lg_nt_4q12r3l_mt_c	1085	nugget_mentioned	0.2777777777777778
lg_nt_4q12r3l_mt_c	1085	nugget_coverage	0.2222222222222222
lg_nt_4q12r3l_mt_c	1087	sentence_support_opt	0.7857142857142857
lg_nt_4q12r3l_mt_c	1087	sentence_support_pes	0.7142857142857143
lg_nt_4q12r3l_mt_c	1087	sentence_support_llmfilled	0.7142857142857143
lg_nt_4q12r3l_mt_c	1087	nugget_mentioned	0.6666666666666666
lg_nt_4q12r3l_mt_c	1087	nugget_coverage	0.5
lg_nt_4q12r3l_mt_c	all	sentence_support_opt	0.8026351562296745
lg_nt_4q12r3l_mt_c	all	sentence_support_pes	0.48678935633156173
lg_nt_4q12r3l_mt_c	all	sentence_support_llmfilled	0.48678935633156184
lg_nt_4q12r3l_mt_c	all	nugget_mentioned	0.3000916559512444
lg_nt_4q12r3l_mt_c	all	nugget_coverage	0.20112997117413434
