run_id	request_id	metric	value
v3_surround_glm4	all	sentences	129.0
v3_surround_glm4	all	sentences_with_citations_or_requiring_citations	129.0
v3_surround_glm4	all	correctly_cited_sentences	45.0
v3_surround_glm4	all	nuggets	815.0
v3_surround_glm4	all	nuggets_weighted	477.0
v3_surround_glm4	all	correct_nuggets	114.0
v3_surround_glm4	all	correct_nuggets_weighted	89.0
v3_surround_glm4	all	citations	377.0
v3_surround_glm4	all	relevant_citations	112.0
v3_surround_glm4	all	supporting_citations	163.0
v3_surround_glm4	all	character_count_median	2000.0
v3_surround_glm4	all	character_count_max	2000.0
v3_surround_glm4	all	citation_relevance_micro	0.29708222811671087
v3_surround_glm4	all	citation_relevance_macro	0.21581810328871343
v3_surround_glm4	all	citation_support_micro	0.4323607427055703
v3_surround_glm4	all	citation_support_macro	0.27255281548323085
v3_surround_glm4	all	sentence_support_micro	0.3488372093023256
v3_surround_glm4	all	sentence_support_macro	0.22251966783216784
v3_surround_glm4	all	nugget_coverage_micro	0.13987730061349693
v3_surround_glm4	all	nugget_coverage_macro	0.1682821825128357
v3_surround_glm4	all	nugget_coverage_weighted_micro	0.18658280922431866
v3_surround_glm4	all	nugget_coverage_weighted_macro	0.1902599332790865
v3_surround_glm4	all	f1_micro	0.19968470835522856
v3_surround_glm4	all	f1_macro	0.16835233971327027
v3_surround_glm4	all	f1_weighted_micro	0.24312511382261887
v3_surround_glm4	all	f1_weighted_macro	0.18060156129533725
v3_surround_glm4	1001	sentences	16.0
v3_surround_glm4	1001	character_count	2000.0
v3_surround_glm4	1001	sentences_with_citations_or_requiring_citations	16.0
v3_surround_glm4	1001	correctly_cited_sentences	6.0
v3_surround_glm4	1001	nuggets	101.0
v3_surround_glm4	1001	nuggets_weighted	110.0
v3_surround_glm4	1001	correct_nuggets	16.0
v3_surround_glm4	1001	correct_nuggets_weighted	18.0
v3_surround_glm4	1001	citations	38.0
v3_surround_glm4	1001	relevant_citations	29.0
v3_surround_glm4	1001	supporting_citations	18.0
v3_surround_glm4	1001	citation_relevance	0.7631578947368421
v3_surround_glm4	1001	citation_support	0.47368421052631576
v3_surround_glm4	1001	sentence_support	0.375
v3_surround_glm4	1001	nugget_coverage	0.15841584158415842
v3_surround_glm4	1001	nugget_coverage_weighted	0.16363636363636364
v3_surround_glm4	1001	f1	0.22273781902552203
v3_surround_glm4	1001	f1_weighted	0.2278481012658228
v3_surround_glm4	1003	sentences	11.0
v3_surround_glm4	1003	character_count	2000.0
v3_surround_glm4	1003	sentences_with_citations_or_requiring_citations	11.0
v3_surround_glm4	1003	correctly_cited_sentences	4.0
v3_surround_glm4	1003	nuggets	103.0
v3_surround_glm4	1003	nuggets_weighted	26.0
v3_surround_glm4	1003	correct_nuggets	16.0
v3_surround_glm4	1003	correct_nuggets_weighted	8.0
v3_surround_glm4	1003	citations	33.0
v3_surround_glm4	1003	relevant_citations	22.0
v3_surround_glm4	1003	supporting_citations	10.0
v3_surround_glm4	1003	citation_relevance	0.6666666666666666
v3_surround_glm4	1003	citation_support	0.30303030303030304
v3_surround_glm4	1003	sentence_support	0.36363636363636365
v3_surround_glm4	1003	nugget_coverage	0.1553398058252427
v3_surround_glm4	1003	nugget_coverage_weighted	0.3076923076923077
v3_surround_glm4	1003	f1	0.21768707482993194
v3_surround_glm4	1003	f1_weighted	0.33333333333333337
v3_surround_glm4	1005	sentences	13.0
v3_surround_glm4	1005	character_count	2000.0
v3_surround_glm4	1005	sentences_with_citations_or_requiring_citations	13.0
v3_surround_glm4	1005	correctly_cited_sentences	7.0
v3_surround_glm4	1005	nuggets	111.0
v3_surround_glm4	1005	nuggets_weighted	32.0
v3_surround_glm4	1005	correct_nuggets	14.0
v3_surround_glm4	1005	correct_nuggets_weighted	6.0
v3_surround_glm4	1005	citations	37.0
v3_surround_glm4	1005	relevant_citations	16.0
v3_surround_glm4	1005	supporting_citations	18.0
v3_surround_glm4	1005	citation_relevance	0.43243243243243246
v3_surround_glm4	1005	citation_support	0.4864864864864865
v3_surround_glm4	1005	sentence_support	0.5384615384615384
v3_surround_glm4	1005	nugget_coverage	0.12612612612612611
v3_surround_glm4	1005	nugget_coverage_weighted	0.1875
v3_surround_glm4	1005	f1	0.2043795620437956
v3_surround_glm4	1005	f1_weighted	0.27814569536423844
v3_surround_glm4	1007	sentences	1.0
v3_surround_glm4	1007	character_count	13.0
v3_surround_glm4	1007	sentences_with_citations_or_requiring_citations	1.0
v3_surround_glm4	1007	correctly_cited_sentences	0.0
v3_surround_glm4	1007	nuggets	22.0
v3_surround_glm4	1007	nuggets_weighted	6.0
v3_surround_glm4	1007	correct_nuggets	0.0
v3_surround_glm4	1007	correct_nuggets_weighted	0.0
v3_surround_glm4	1007	citations	1.0
v3_surround_glm4	1007	relevant_citations	0.0
v3_surround_glm4	1007	supporting_citations	0.0
v3_surround_glm4	1007	citation_relevance	0.0
v3_surround_glm4	1007	citation_support	0.0
v3_surround_glm4	1007	sentence_support	0.0
v3_surround_glm4	1007	nugget_coverage	0.0
v3_surround_glm4	1007	nugget_coverage_weighted	0.0
v3_surround_glm4	1007	f1	0.0
v3_surround_glm4	1007	f1_weighted	0.0
v3_surround_glm4	1009	sentences	1.0
v3_surround_glm4	1009	character_count	13.0
v3_surround_glm4	1009	sentences_with_citations_or_requiring_citations	1.0
v3_surround_glm4	1009	correctly_cited_sentences	0.0
v3_surround_glm4	1009	nuggets	15.0
v3_surround_glm4	1009	nuggets_weighted	8.0
v3_surround_glm4	1009	correct_nuggets	0.0
v3_surround_glm4	1009	correct_nuggets_weighted	0.0
v3_surround_glm4	1009	citations	1.0
v3_surround_glm4	1009	relevant_citations	0.0
v3_surround_glm4	1009	supporting_citations	0.0
v3_surround_glm4	1009	citation_relevance	0.0
v3_surround_glm4	1009	citation_support	0.0
v3_surround_glm4	1009	sentence_support	0.0
v3_surround_glm4	1009	nugget_coverage	0.0
v3_surround_glm4	1009	nugget_coverage_weighted	0.0
v3_surround_glm4	1009	f1	0.0
v3_surround_glm4	1009	f1_weighted	0.0
v3_surround_glm4	1011	sentences	12.0
v3_surround_glm4	1011	character_count	2000.0
v3_surround_glm4	1011	sentences_with_citations_or_requiring_citations	12.0
v3_surround_glm4	1011	correctly_cited_sentences	5.0
v3_surround_glm4	1011	nuggets	63.0
v3_surround_glm4	1011	nuggets_weighted	40.0
v3_surround_glm4	1011	correct_nuggets	15.0
v3_surround_glm4	1011	correct_nuggets_weighted	6.0
v3_surround_glm4	1011	citations	53.0
v3_surround_glm4	1011	relevant_citations	7.0
v3_surround_glm4	1011	supporting_citations	29.0
v3_surround_glm4	1011	citation_relevance	0.1320754716981132
v3_surround_glm4	1011	citation_support	0.5471698113207547
v3_surround_glm4	1011	sentence_support	0.4166666666666667
v3_surround_glm4	1011	nugget_coverage	0.23809523809523808
v3_surround_glm4	1011	nugget_coverage_weighted	0.15
v3_surround_glm4	1011	f1	0.30303030303030304
v3_surround_glm4	1011	f1_weighted	0.22058823529411764
v3_surround_glm4	1013	sentences	1.0
v3_surround_glm4	1013	character_count	13.0
v3_surround_glm4	1013	sentences_with_citations_or_requiring_citations	1.0
v3_surround_glm4	1013	correctly_cited_sentences	0.0
v3_surround_glm4	1013	nuggets	26.0
v3_surround_glm4	1013	nuggets_weighted	12.0
v3_surround_glm4	1013	correct_nuggets	0.0
v3_surround_glm4	1013	correct_nuggets_weighted	0.0
v3_surround_glm4	1013	citations	1.0
v3_surround_glm4	1013	relevant_citations	0.0
v3_surround_glm4	1013	supporting_citations	0.0
v3_surround_glm4	1013	citation_relevance	0.0
v3_surround_glm4	1013	citation_support	0.0
v3_surround_glm4	1013	sentence_support	0.0
v3_surround_glm4	1013	nugget_coverage	0.0
v3_surround_glm4	1013	nugget_coverage_weighted	0.0
v3_surround_glm4	1013	f1	0.0
v3_surround_glm4	1013	f1_weighted	0.0
v3_surround_glm4	1017	sentences	13.0
v3_surround_glm4	1017	character_count	2000.0
v3_surround_glm4	1017	sentences_with_citations_or_requiring_citations	13.0
v3_surround_glm4	1017	correctly_cited_sentences	4.0
v3_surround_glm4	1017	nuggets	109.0
v3_surround_glm4	1017	nuggets_weighted	62.0
v3_surround_glm4	1017	correct_nuggets	16.0
v3_surround_glm4	1017	correct_nuggets_weighted	14.0
v3_surround_glm4	1017	citations	48.0
v3_surround_glm4	1017	relevant_citations	4.0
v3_surround_glm4	1017	supporting_citations	15.0
v3_surround_glm4	1017	citation_relevance	0.08333333333333333
v3_surround_glm4	1017	citation_support	0.3125
v3_surround_glm4	1017	sentence_support	0.3076923076923077
v3_surround_glm4	1017	nugget_coverage	0.14678899082568808
v3_surround_glm4	1017	nugget_coverage_weighted	0.22580645161290322
v3_surround_glm4	1017	f1	0.19875776397515527
v3_surround_glm4	1017	f1_weighted	0.26046511627906976
v3_surround_glm4	1025	sentences	8.0
v3_surround_glm4	1025	character_count	2000.0
v3_surround_glm4	1025	sentences_with_citations_or_requiring_citations	8.0
v3_surround_glm4	1025	correctly_cited_sentences	2.0
v3_surround_glm4	1025	nuggets	12.0
v3_surround_glm4	1025	nuggets_weighted	20.0
v3_surround_glm4	1025	correct_nuggets	8.0
v3_surround_glm4	1025	correct_nuggets_weighted	14.0
v3_surround_glm4	1025	citations	42.0
v3_surround_glm4	1025	relevant_citations	7.0
v3_surround_glm4	1025	supporting_citations	25.0
v3_surround_glm4	1025	citation_relevance	0.16666666666666666
v3_surround_glm4	1025	citation_support	0.5952380952380952
v3_surround_glm4	1025	sentence_support	0.25
v3_surround_glm4	1025	nugget_coverage	0.6666666666666666
v3_surround_glm4	1025	nugget_coverage_weighted	0.7
v3_surround_glm4	1025	f1	0.36363636363636365
v3_surround_glm4	1025	f1_weighted	0.3684210526315789
v3_surround_glm4	1027	sentences	12.0
v3_surround_glm4	1027	character_count	2000.0
v3_surround_glm4	1027	sentences_with_citations_or_requiring_citations	12.0
v3_surround_glm4	1027	correctly_cited_sentences	4.0
v3_surround_glm4	1027	nuggets	7.0
v3_surround_glm4	1027	nuggets_weighted	10.0
v3_surround_glm4	1027	correct_nuggets	3.0
v3_surround_glm4	1027	correct_nuggets_weighted	6.0
v3_surround_glm4	1027	citations	34.0
v3_surround_glm4	1027	relevant_citations	14.0
v3_surround_glm4	1027	supporting_citations	19.0
v3_surround_glm4	1027	citation_relevance	0.4117647058823529
v3_surround_glm4	1027	citation_support	0.5588235294117647
v3_surround_glm4	1027	sentence_support	0.3333333333333333
v3_surround_glm4	1027	nugget_coverage	0.42857142857142855
v3_surround_glm4	1027	nugget_coverage_weighted	0.6
v3_surround_glm4	1027	f1	0.375
v3_surround_glm4	1027	f1_weighted	0.42857142857142855
v3_surround_glm4	1029	sentences	1.0
v3_surround_glm4	1029	character_count	13.0
v3_surround_glm4	1029	sentences_with_citations_or_requiring_citations	1.0
v3_surround_glm4	1029	correctly_cited_sentences	0.0
v3_surround_glm4	1029	nuggets	106.0
v3_surround_glm4	1029	nuggets_weighted	58.0
v3_surround_glm4	1029	correct_nuggets	0.0
v3_surround_glm4	1029	correct_nuggets_weighted	0.0
v3_surround_glm4	1029	citations	1.0
v3_surround_glm4	1029	relevant_citations	0.0
v3_surround_glm4	1029	supporting_citations	0.0
v3_surround_glm4	1029	citation_relevance	0.0
v3_surround_glm4	1029	citation_support	0.0
v3_surround_glm4	1029	sentence_support	0.0
v3_surround_glm4	1029	nugget_coverage	0.0
v3_surround_glm4	1029	nugget_coverage_weighted	0.0
v3_surround_glm4	1029	f1	0.0
v3_surround_glm4	1029	f1_weighted	0.0
v3_surround_glm4	1033	sentences	11.0
v3_surround_glm4	1033	character_count	2000.0
v3_surround_glm4	1033	sentences_with_citations_or_requiring_citations	11.0
v3_surround_glm4	1033	correctly_cited_sentences	1.0
v3_surround_glm4	1033	nuggets	56.0
v3_surround_glm4	1033	nuggets_weighted	28.0
v3_surround_glm4	1033	correct_nuggets	10.0
v3_surround_glm4	1033	correct_nuggets_weighted	4.0
v3_surround_glm4	1033	citations	53.0
v3_surround_glm4	1033	relevant_citations	0.0
v3_surround_glm4	1033	supporting_citations	17.0
v3_surround_glm4	1033	citation_relevance	0.0
v3_surround_glm4	1033	citation_support	0.32075471698113206
v3_surround_glm4	1033	sentence_support	0.09090909090909091
v3_surround_glm4	1033	nugget_coverage	0.17857142857142858
v3_surround_glm4	1033	nugget_coverage_weighted	0.14285714285714285
v3_surround_glm4	1033	f1	0.12048192771084339
v3_surround_glm4	1033	f1_weighted	0.1111111111111111
v3_surround_glm4	1041	sentences	14.0
v3_surround_glm4	1041	character_count	2000.0
v3_surround_glm4	1041	sentences_with_citations_or_requiring_citations	14.0
v3_surround_glm4	1041	correctly_cited_sentences	7.0
v3_surround_glm4	1041	nuggets	22.0
v3_surround_glm4	1041	nuggets_weighted	10.0
v3_surround_glm4	1041	correct_nuggets	5.0
v3_surround_glm4	1041	correct_nuggets_weighted	2.0
v3_surround_glm4	1041	citations	14.0
v3_surround_glm4	1041	relevant_citations	6.0
v3_surround_glm4	1041	supporting_citations	7.0
v3_surround_glm4	1041	citation_relevance	0.42857142857142855
v3_surround_glm4	1041	citation_support	0.5
v3_surround_glm4	1041	sentence_support	0.5
v3_surround_glm4	1041	nugget_coverage	0.22727272727272727
v3_surround_glm4	1041	nugget_coverage_weighted	0.2
v3_surround_glm4	1041	f1	0.3125
v3_surround_glm4	1041	f1_weighted	0.28571428571428575
v3_surround_glm4	1053	sentences	1.0
v3_surround_glm4	1053	character_count	13.0
v3_surround_glm4	1053	sentences_with_citations_or_requiring_citations	1.0
v3_surround_glm4	1053	correctly_cited_sentences	0.0
v3_surround_glm4	1053	nuggets	21.0
v3_surround_glm4	1053	nuggets_weighted	14.0
v3_surround_glm4	1053	correct_nuggets	0.0
v3_surround_glm4	1053	correct_nuggets_weighted	0.0
v3_surround_glm4	1053	citations	1.0
v3_surround_glm4	1053	relevant_citations	0.0
v3_surround_glm4	1053	supporting_citations	0.0
v3_surround_glm4	1053	citation_relevance	0.0
v3_surround_glm4	1053	citation_support	0.0
v3_surround_glm4	1053	sentence_support	0.0
v3_surround_glm4	1053	nugget_coverage	0.0
v3_surround_glm4	1053	nugget_coverage_weighted	0.0
v3_surround_glm4	1053	f1	0.0
v3_surround_glm4	1053	f1_weighted	0.0
v3_surround_glm4	1065	sentences	13.0
v3_surround_glm4	1065	character_count	2000.0
v3_surround_glm4	1065	sentences_with_citations_or_requiring_citations	13.0
v3_surround_glm4	1065	correctly_cited_sentences	5.0
v3_surround_glm4	1065	nuggets	30.0
v3_surround_glm4	1065	nuggets_weighted	30.0
v3_surround_glm4	1065	correct_nuggets	11.0
v3_surround_glm4	1065	correct_nuggets_weighted	11.0
v3_surround_glm4	1065	citations	19.0
v3_surround_glm4	1065	relevant_citations	7.0
v3_surround_glm4	1065	supporting_citations	5.0
v3_surround_glm4	1065	citation_relevance	0.3684210526315789
v3_surround_glm4	1065	citation_support	0.2631578947368421
v3_surround_glm4	1065	sentence_support	0.38461538461538464
v3_surround_glm4	1065	nugget_coverage	0.36666666666666664
v3_surround_glm4	1065	nugget_coverage_weighted	0.36666666666666664
v3_surround_glm4	1065	f1	0.37542662116040953
v3_surround_glm4	1065	f1_weighted	0.37542662116040953
v3_surround_glm4	1069	sentences	1.0
v3_surround_glm4	1069	character_count	13.0
v3_surround_glm4	1069	sentences_with_citations_or_requiring_citations	1.0
v3_surround_glm4	1069	correctly_cited_sentences	0.0
v3_surround_glm4	1069	nuggets	11.0
v3_surround_glm4	1069	nuggets_weighted	11.0
v3_surround_glm4	1069	correct_nuggets	0.0
v3_surround_glm4	1069	correct_nuggets_weighted	0.0
v3_surround_glm4	1069	citations	1.0
v3_surround_glm4	1069	relevant_citations	0.0
v3_surround_glm4	1069	supporting_citations	0.0
v3_surround_glm4	1069	citation_relevance	0.0
v3_surround_glm4	1069	citation_support	0.0
v3_surround_glm4	1069	sentence_support	0.0
v3_surround_glm4	1069	nugget_coverage	0.0
v3_surround_glm4	1069	nugget_coverage_weighted	0.0
v3_surround_glm4	1069	f1	0.0
v3_surround_glm4	1069	f1_weighted	0.0