run_id	request_id	metric	value
hltime-lg.qwen	all	sentences	234.0
hltime-lg.qwen	all	sentences_with_citations_or_requiring_citations	225.0
hltime-lg.qwen	all	correctly_cited_sentences	165.0
hltime-lg.qwen	all	first_instance_sentences_missing_citation	1.0
hltime-lg.qwen	all	nuggets	815.0
hltime-lg.qwen	all	nuggets_weighted	477.0
hltime-lg.qwen	all	correct_nuggets	253.0
hltime-lg.qwen	all	correct_nuggets_weighted	186.0
hltime-lg.qwen	all	citations	271.0
hltime-lg.qwen	all	relevant_citations	112.0
hltime-lg.qwen	all	supporting_citations	203.0
hltime-lg.qwen	all	character_count_median	1769.0
hltime-lg.qwen	all	character_count_max	1965.0
hltime-lg.qwen	all	citation_relevance_micro	0.4132841328413284
hltime-lg.qwen	all	citation_relevance_macro	0.39840818903318903
hltime-lg.qwen	all	citation_support_micro	0.7490774907749077
hltime-lg.qwen	all	citation_support_macro	0.7238478535353535
hltime-lg.qwen	all	sentence_support_micro	0.7333333333333333
hltime-lg.qwen	all	sentence_support_macro	0.7154456654456653
hltime-lg.qwen	all	nugget_coverage_micro	0.3104294478527607
hltime-lg.qwen	all	nugget_coverage_macro	0.39383969048815626
hltime-lg.qwen	all	nugget_coverage_weighted_micro	0.389937106918239
hltime-lg.qwen	all	nugget_coverage_weighted_macro	0.4241725353229455
hltime-lg.qwen	all	f1_micro	0.43620689655172407
hltime-lg.qwen	all	f1_macro	0.47870743016457024
hltime-lg.qwen	all	f1_weighted_micro	0.5091452034341173
hltime-lg.qwen	all	f1_weighted_macro	0.47914609881684245
hltime-lg.qwen	1001	sentences	15.0
hltime-lg.qwen	1001	character_count	1728.0
hltime-lg.qwen	1001	sentences_with_citations_or_requiring_citations	15.0
hltime-lg.qwen	1001	correctly_cited_sentences	11.0
hltime-lg.qwen	1001	nuggets	101.0
hltime-lg.qwen	1001	nuggets_weighted	110.0
hltime-lg.qwen	1001	correct_nuggets	45.0
hltime-lg.qwen	1001	correct_nuggets_weighted	50.0
hltime-lg.qwen	1001	citations	15.0
hltime-lg.qwen	1001	relevant_citations	3.0
hltime-lg.qwen	1001	supporting_citations	11.0
hltime-lg.qwen	1001	citation_relevance	0.2
hltime-lg.qwen	1001	citation_support	0.7333333333333333
hltime-lg.qwen	1001	sentence_support	0.7333333333333333
hltime-lg.qwen	1001	nugget_coverage	0.44554455445544555
hltime-lg.qwen	1001	nugget_coverage_weighted	0.45454545454545453
hltime-lg.qwen	1001	f1	0.5543113101903695
hltime-lg.qwen	1001	f1_weighted	0.5612244897959184
hltime-lg.qwen	1003	sentences	14.0
hltime-lg.qwen	1003	character_count	1732.0
hltime-lg.qwen	1003	sentences_with_citations_or_requiring_citations	14.0
hltime-lg.qwen	1003	correctly_cited_sentences	9.0
hltime-lg.qwen	1003	nuggets	103.0
hltime-lg.qwen	1003	nuggets_weighted	26.0
hltime-lg.qwen	1003	correct_nuggets	17.0
hltime-lg.qwen	1003	correct_nuggets_weighted	10.0
hltime-lg.qwen	1003	citations	14.0
hltime-lg.qwen	1003	relevant_citations	8.0
hltime-lg.qwen	1003	supporting_citations	9.0
hltime-lg.qwen	1003	citation_relevance	0.5714285714285714
hltime-lg.qwen	1003	citation_support	0.6428571428571429
hltime-lg.qwen	1003	sentence_support	0.6428571428571429
hltime-lg.qwen	1003	nugget_coverage	0.1650485436893204
hltime-lg.qwen	1003	nugget_coverage_weighted	0.38461538461538464
hltime-lg.qwen	1003	f1	0.26266094420600855
hltime-lg.qwen	1003	f1_weighted	0.4812834224598931
hltime-lg.qwen	1005	sentences	18.0
hltime-lg.qwen	1005	character_count	1965.0
hltime-lg.qwen	1005	sentences_with_citations_or_requiring_citations	18.0
hltime-lg.qwen	1005	correctly_cited_sentences	15.0
hltime-lg.qwen	1005	nuggets	111.0
hltime-lg.qwen	1005	nuggets_weighted	32.0
hltime-lg.qwen	1005	correct_nuggets	24.0
hltime-lg.qwen	1005	correct_nuggets_weighted	6.0
hltime-lg.qwen	1005	citations	18.0
hltime-lg.qwen	1005	relevant_citations	9.0
hltime-lg.qwen	1005	supporting_citations	15.0
hltime-lg.qwen	1005	citation_relevance	0.5
hltime-lg.qwen	1005	citation_support	0.8333333333333334
hltime-lg.qwen	1005	sentence_support	0.8333333333333334
hltime-lg.qwen	1005	nugget_coverage	0.21621621621621623
hltime-lg.qwen	1005	nugget_coverage_weighted	0.1875
hltime-lg.qwen	1005	f1	0.34334763948497854
hltime-lg.qwen	1005	f1_weighted	0.3061224489795918
hltime-lg.qwen	1007	sentences	18.0
hltime-lg.qwen	1007	character_count	1656.0
hltime-lg.qwen	1007	sentences_with_citations_or_requiring_citations	18.0
hltime-lg.qwen	1007	correctly_cited_sentences	16.0
hltime-lg.qwen	1007	nuggets	22.0
hltime-lg.qwen	1007	nuggets_weighted	6.0
hltime-lg.qwen	1007	correct_nuggets	13.0
hltime-lg.qwen	1007	correct_nuggets_weighted	2.0
hltime-lg.qwen	1007	citations	18.0
hltime-lg.qwen	1007	relevant_citations	14.0
hltime-lg.qwen	1007	supporting_citations	16.0
hltime-lg.qwen	1007	citation_relevance	0.7777777777777778
hltime-lg.qwen	1007	citation_support	0.8888888888888888
hltime-lg.qwen	1007	sentence_support	0.8888888888888888
hltime-lg.qwen	1007	nugget_coverage	0.5909090909090909
hltime-lg.qwen	1007	nugget_coverage_weighted	0.3333333333333333
hltime-lg.qwen	1007	f1	0.7098976109215018
hltime-lg.qwen	1007	f1_weighted	0.48484848484848486
hltime-lg.qwen	1009	sentences	13.0
hltime-lg.qwen	1009	character_count	1679.0
hltime-lg.qwen	1009	sentences_with_citations_or_requiring_citations	13.0
hltime-lg.qwen	1009	correctly_cited_sentences	10.0
hltime-lg.qwen	1009	nuggets	15.0
hltime-lg.qwen	1009	nuggets_weighted	8.0
hltime-lg.qwen	1009	correct_nuggets	9.0
hltime-lg.qwen	1009	correct_nuggets_weighted	4.0
hltime-lg.qwen	1009	citations	14.0
hltime-lg.qwen	1009	relevant_citations	5.0
hltime-lg.qwen	1009	supporting_citations	11.0
hltime-lg.qwen	1009	citation_relevance	0.35714285714285715
hltime-lg.qwen	1009	citation_support	0.7857142857142857
hltime-lg.qwen	1009	sentence_support	0.7692307692307693
hltime-lg.qwen	1009	nugget_coverage	0.6
hltime-lg.qwen	1009	nugget_coverage_weighted	0.5
hltime-lg.qwen	1009	f1	0.6741573033707865
hltime-lg.qwen	1009	f1_weighted	0.6060606060606061
hltime-lg.qwen	1011	sentences	15.0
hltime-lg.qwen	1011	character_count	1806.0
hltime-lg.qwen	1011	sentences_with_citations_or_requiring_citations	15.0
hltime-lg.qwen	1011	correctly_cited_sentences	14.0
hltime-lg.qwen	1011	nuggets	63.0
hltime-lg.qwen	1011	nuggets_weighted	40.0
hltime-lg.qwen	1011	correct_nuggets	24.0
hltime-lg.qwen	1011	correct_nuggets_weighted	14.0
hltime-lg.qwen	1011	citations	15.0
hltime-lg.qwen	1011	relevant_citations	0.0
hltime-lg.qwen	1011	supporting_citations	14.0
hltime-lg.qwen	1011	citation_relevance	0.0
hltime-lg.qwen	1011	citation_support	0.9333333333333333
hltime-lg.qwen	1011	sentence_support	0.9333333333333333
hltime-lg.qwen	1011	nugget_coverage	0.38095238095238093
hltime-lg.qwen	1011	nugget_coverage_weighted	0.35
hltime-lg.qwen	1011	f1	0.5410628019323672
hltime-lg.qwen	1011	f1_weighted	0.5090909090909091
hltime-lg.qwen	1013	sentences	13.0
hltime-lg.qwen	1013	character_count	1734.0
hltime-lg.qwen	1013	sentences_with_citations_or_requiring_citations	13.0
hltime-lg.qwen	1013	correctly_cited_sentences	9.0
hltime-lg.qwen	1013	nuggets	26.0
hltime-lg.qwen	1013	nuggets_weighted	12.0
hltime-lg.qwen	1013	correct_nuggets	15.0
hltime-lg.qwen	1013	correct_nuggets_weighted	12.0
hltime-lg.qwen	1013	citations	18.0
hltime-lg.qwen	1013	relevant_citations	10.0
hltime-lg.qwen	1013	supporting_citations	13.0
hltime-lg.qwen	1013	citation_relevance	0.5555555555555556
hltime-lg.qwen	1013	citation_support	0.7222222222222222
hltime-lg.qwen	1013	sentence_support	0.6923076923076923
hltime-lg.qwen	1013	nugget_coverage	0.5769230769230769
hltime-lg.qwen	1013	nugget_coverage_weighted	1.0
hltime-lg.qwen	1013	f1	0.6293706293706293
hltime-lg.qwen	1013	f1_weighted	0.8181818181818181
hltime-lg.qwen	1017	sentences	15.0
hltime-lg.qwen	1017	character_count	1843.0
hltime-lg.qwen	1017	sentences_with_citations_or_requiring_citations	15.0
hltime-lg.qwen	1017	correctly_cited_sentences	12.0
hltime-lg.qwen	1017	nuggets	109.0
hltime-lg.qwen	1017	nuggets_weighted	62.0
hltime-lg.qwen	1017	correct_nuggets	26.0
hltime-lg.qwen	1017	correct_nuggets_weighted	26.0
hltime-lg.qwen	1017	citations	15.0
hltime-lg.qwen	1017	relevant_citations	9.0
hltime-lg.qwen	1017	supporting_citations	12.0
hltime-lg.qwen	1017	citation_relevance	0.6
hltime-lg.qwen	1017	citation_support	0.8
hltime-lg.qwen	1017	sentence_support	0.8
hltime-lg.qwen	1017	nugget_coverage	0.23853211009174313
hltime-lg.qwen	1017	nugget_coverage_weighted	0.41935483870967744
hltime-lg.qwen	1017	f1	0.36749116607773846
hltime-lg.qwen	1017	f1_weighted	0.5502645502645502
hltime-lg.qwen	1025	sentences	18.0
hltime-lg.qwen	1025	character_count	1921.0
hltime-lg.qwen	1025	sentences_with_citations_or_requiring_citations	18.0
hltime-lg.qwen	1025	correctly_cited_sentences	17.0
hltime-lg.qwen	1025	nuggets	12.0
hltime-lg.qwen	1025	nuggets_weighted	20.0
hltime-lg.qwen	1025	correct_nuggets	8.0
hltime-lg.qwen	1025	correct_nuggets_weighted	12.0
hltime-lg.qwen	1025	citations	21.0
hltime-lg.qwen	1025	relevant_citations	14.0
hltime-lg.qwen	1025	supporting_citations	19.0
hltime-lg.qwen	1025	citation_relevance	0.6666666666666666
hltime-lg.qwen	1025	citation_support	0.9047619047619048
hltime-lg.qwen	1025	sentence_support	0.9444444444444444
hltime-lg.qwen	1025	nugget_coverage	0.6666666666666666
hltime-lg.qwen	1025	nugget_coverage_weighted	0.6
hltime-lg.qwen	1025	f1	0.7816091954022987
hltime-lg.qwen	1025	f1_weighted	0.7338129496402879
hltime-lg.qwen	1027	sentences	18.0
hltime-lg.qwen	1027	character_count	1887.0
hltime-lg.qwen	1027	sentences_with_citations_or_requiring_citations	9.0
hltime-lg.qwen	1027	correctly_cited_sentences	5.0
hltime-lg.qwen	1027	first_instance_sentences_missing_citation	1.0
hltime-lg.qwen	1027	nuggets	7.0
hltime-lg.qwen	1027	nuggets_weighted	10.0
hltime-lg.qwen	1027	correct_nuggets	5.0
hltime-lg.qwen	1027	correct_nuggets_weighted	8.0
hltime-lg.qwen	1027	citations	8.0
hltime-lg.qwen	1027	relevant_citations	0.0
hltime-lg.qwen	1027	supporting_citations	5.0
hltime-lg.qwen	1027	citation_relevance	0.0
hltime-lg.qwen	1027	citation_support	0.625
hltime-lg.qwen	1027	sentence_support	0.5555555555555556
hltime-lg.qwen	1027	nugget_coverage	0.7142857142857143
hltime-lg.qwen	1027	nugget_coverage_weighted	0.8
hltime-lg.qwen	1027	f1	0.6250000000000001
hltime-lg.qwen	1027	f1_weighted	0.6557377049180328
hltime-lg.qwen	1029	sentences	15.0
hltime-lg.qwen	1029	character_count	1863.0
hltime-lg.qwen	1029	sentences_with_citations_or_requiring_citations	15.0
hltime-lg.qwen	1029	correctly_cited_sentences	10.0
hltime-lg.qwen	1029	nuggets	106.0
hltime-lg.qwen	1029	nuggets_weighted	58.0
hltime-lg.qwen	1029	correct_nuggets	22.0
hltime-lg.qwen	1029	correct_nuggets_weighted	8.0
hltime-lg.qwen	1029	citations	15.0
hltime-lg.qwen	1029	relevant_citations	7.0
hltime-lg.qwen	1029	supporting_citations	10.0
hltime-lg.qwen	1029	citation_relevance	0.4666666666666667
hltime-lg.qwen	1029	citation_support	0.6666666666666666
hltime-lg.qwen	1029	sentence_support	0.6666666666666666
hltime-lg.qwen	1029	nugget_coverage	0.20754716981132076
hltime-lg.qwen	1029	nugget_coverage_weighted	0.13793103448275862
hltime-lg.qwen	1029	f1	0.31654676258992803
hltime-lg.qwen	1029	f1_weighted	0.2285714285714286
hltime-lg.qwen	1033	sentences	12.0
hltime-lg.qwen	1033	character_count	1576.0
hltime-lg.qwen	1033	sentences_with_citations_or_requiring_citations	12.0
hltime-lg.qwen	1033	correctly_cited_sentences	10.0
hltime-lg.qwen	1033	nuggets	56.0
hltime-lg.qwen	1033	nuggets_weighted	28.0
hltime-lg.qwen	1033	correct_nuggets	21.0
hltime-lg.qwen	1033	correct_nuggets_weighted	20.0
hltime-lg.qwen	1033	citations	36.0
hltime-lg.qwen	1033	relevant_citations	13.0
hltime-lg.qwen	1033	supporting_citations	34.0
hltime-lg.qwen	1033	citation_relevance	0.3611111111111111
hltime-lg.qwen	1033	citation_support	0.9444444444444444
hltime-lg.qwen	1033	sentence_support	0.8333333333333334
hltime-lg.qwen	1033	nugget_coverage	0.375
hltime-lg.qwen	1033	nugget_coverage_weighted	0.7142857142857143
hltime-lg.qwen	1033	f1	0.5172413793103448
hltime-lg.qwen	1033	f1_weighted	0.7692307692307692
hltime-lg.qwen	1041	sentences	13.0
hltime-lg.qwen	1041	character_count	1869.0
hltime-lg.qwen	1041	sentences_with_citations_or_requiring_citations	13.0
hltime-lg.qwen	1041	correctly_cited_sentences	7.0
hltime-lg.qwen	1041	nuggets	22.0
hltime-lg.qwen	1041	nuggets_weighted	10.0
hltime-lg.qwen	1041	correct_nuggets	9.0
hltime-lg.qwen	1041	correct_nuggets_weighted	0.0
hltime-lg.qwen	1041	citations	22.0
hltime-lg.qwen	1041	relevant_citations	7.0
hltime-lg.qwen	1041	supporting_citations	12.0
hltime-lg.qwen	1041	citation_relevance	0.3181818181818182
hltime-lg.qwen	1041	citation_support	0.5454545454545454
hltime-lg.qwen	1041	sentence_support	0.5384615384615384
hltime-lg.qwen	1041	nugget_coverage	0.4090909090909091
hltime-lg.qwen	1041	nugget_coverage_weighted	0.0
hltime-lg.qwen	1041	f1	0.4649446494464945
hltime-lg.qwen	1041	f1_weighted	0.0
hltime-lg.qwen	1053	sentences	12.0
hltime-lg.qwen	1053	character_count	1804.0
hltime-lg.qwen	1053	sentences_with_citations_or_requiring_citations	12.0
hltime-lg.qwen	1053	correctly_cited_sentences	7.0
hltime-lg.qwen	1053	nuggets	21.0
hltime-lg.qwen	1053	nuggets_weighted	14.0
hltime-lg.qwen	1053	correct_nuggets	11.0
hltime-lg.qwen	1053	correct_nuggets_weighted	10.0
hltime-lg.qwen	1053	citations	12.0
hltime-lg.qwen	1053	relevant_citations	7.0
hltime-lg.qwen	1053	supporting_citations	7.0
hltime-lg.qwen	1053	citation_relevance	0.5833333333333334
hltime-lg.qwen	1053	citation_support	0.5833333333333334
hltime-lg.qwen	1053	sentence_support	0.5833333333333334
hltime-lg.qwen	1053	nugget_coverage	0.5238095238095238
hltime-lg.qwen	1053	nugget_coverage_weighted	0.7142857142857143
hltime-lg.qwen	1053	f1	0.5519713261648745
hltime-lg.qwen	1053	f1_weighted	0.6422018348623854
hltime-lg.qwen	1065	sentences	12.0
hltime-lg.qwen	1065	character_count	1569.0
hltime-lg.qwen	1065	sentences_with_citations_or_requiring_citations	12.0
hltime-lg.qwen	1065	correctly_cited_sentences	5.0
hltime-lg.qwen	1065	nuggets	30.0
hltime-lg.qwen	1065	nuggets_weighted	30.0
hltime-lg.qwen	1065	correct_nuggets	3.0
hltime-lg.qwen	1065	correct_nuggets_weighted	3.0
hltime-lg.qwen	1065	citations	12.0
hltime-lg.qwen	1065	relevant_citations	3.0
hltime-lg.qwen	1065	supporting_citations	5.0
hltime-lg.qwen	1065	citation_relevance	0.25
hltime-lg.qwen	1065	citation_support	0.4166666666666667
hltime-lg.qwen	1065	sentence_support	0.4166666666666667
hltime-lg.qwen	1065	nugget_coverage	0.1
hltime-lg.qwen	1065	nugget_coverage_weighted	0.1
hltime-lg.qwen	1065	f1	0.16129032258064516
hltime-lg.qwen	1065	f1_weighted	0.16129032258064516
hltime-lg.qwen	1069	sentences	13.0
hltime-lg.qwen	1069	character_count	1678.0
hltime-lg.qwen	1069	sentences_with_citations_or_requiring_citations	13.0
hltime-lg.qwen	1069	correctly_cited_sentences	8.0
hltime-lg.qwen	1069	nuggets	11.0
hltime-lg.qwen	1069	nuggets_weighted	11.0
hltime-lg.qwen	1069	correct_nuggets	1.0
hltime-lg.qwen	1069	correct_nuggets_weighted	1.0
hltime-lg.qwen	1069	citations	18.0
hltime-lg.qwen	1069	relevant_citations	3.0
hltime-lg.qwen	1069	supporting_citations	10.0
hltime-lg.qwen	1069	citation_relevance	0.16666666666666666
hltime-lg.qwen	1069	citation_support	0.5555555555555556
hltime-lg.qwen	1069	sentence_support	0.6153846153846154
hltime-lg.qwen	1069	nugget_coverage	0.09090909090909091
hltime-lg.qwen	1069	nugget_coverage_weighted	0.09090909090909091
hltime-lg.qwen	1069	f1	0.15841584158415842
hltime-lg.qwen	1069	f1_weighted	0.15841584158415842