run_id	request_id	metric	value
v2_split_qwen	all	sentences	108.0
v2_split_qwen	all	sentences_with_citations_or_requiring_citations	108.0
v2_split_qwen	all	correctly_cited_sentences	18.0
v2_split_qwen	all	nuggets	815.0
v2_split_qwen	all	nuggets_weighted	477.0
v2_split_qwen	all	correct_nuggets	93.0
v2_split_qwen	all	correct_nuggets_weighted	66.0
v2_split_qwen	all	citations	271.0
v2_split_qwen	all	relevant_citations	60.0
v2_split_qwen	all	supporting_citations	91.0
v2_split_qwen	all	character_count_median	1097.5
v2_split_qwen	all	character_count_max	1206.0
v2_split_qwen	all	citation_relevance_micro	0.22140221402214022
v2_split_qwen	all	citation_relevance_macro	0.1537583860178572
v2_split_qwen	all	citation_support_micro	0.33579335793357934
v2_split_qwen	all	citation_support_macro	0.25308550313947603
v2_split_qwen	all	sentence_support_micro	0.16666666666666666
v2_split_qwen	all	sentence_support_macro	0.15267857142857144
v2_split_qwen	all	nugget_coverage_micro	0.11411042944785275
v2_split_qwen	all	nugget_coverage_macro	0.18770484204095061
v2_split_qwen	all	nugget_coverage_weighted_micro	0.13836477987421383
v2_split_qwen	all	nugget_coverage_weighted_macro	0.1709633033586732
v2_split_qwen	all	f1_micro	0.13546977421704298
v2_split_qwen	all	f1_macro	0.0970046619882447
v2_split_qwen	all	f1_weighted_micro	0.15120274914089346
v2_split_qwen	all	f1_weighted_macro	0.09248456898852611
v2_split_qwen	1001	sentences	9.0
v2_split_qwen	1001	character_count	883.0
v2_split_qwen	1001	sentences_with_citations_or_requiring_citations	9.0
v2_split_qwen	1001	correctly_cited_sentences	2.0
v2_split_qwen	1001	nuggets	101.0
v2_split_qwen	1001	nuggets_weighted	110.0
v2_split_qwen	1001	correct_nuggets	10.0
v2_split_qwen	1001	correct_nuggets_weighted	10.0
v2_split_qwen	1001	citations	36.0
v2_split_qwen	1001	relevant_citations	21.0
v2_split_qwen	1001	supporting_citations	11.0
v2_split_qwen	1001	citation_relevance	0.5833333333333334
v2_split_qwen	1001	citation_support	0.3055555555555556
v2_split_qwen	1001	sentence_support	0.2222222222222222
v2_split_qwen	1001	nugget_coverage	0.09900990099009901
v2_split_qwen	1001	nugget_coverage_weighted	0.09090909090909091
v2_split_qwen	1001	f1	0.13698630136986303
v2_split_qwen	1001	f1_weighted	0.1290322580645161
v2_split_qwen	1003	sentences	9.0
v2_split_qwen	1003	character_count	1168.0
v2_split_qwen	1003	sentences_with_citations_or_requiring_citations	9.0
v2_split_qwen	1003	correctly_cited_sentences	4.0
v2_split_qwen	1003	nuggets	103.0
v2_split_qwen	1003	nuggets_weighted	26.0
v2_split_qwen	1003	correct_nuggets	9.0
v2_split_qwen	1003	correct_nuggets_weighted	4.0
v2_split_qwen	1003	citations	18.0
v2_split_qwen	1003	relevant_citations	6.0
v2_split_qwen	1003	supporting_citations	9.0
v2_split_qwen	1003	citation_relevance	0.3333333333333333
v2_split_qwen	1003	citation_support	0.5
v2_split_qwen	1003	sentence_support	0.4444444444444444
v2_split_qwen	1003	nugget_coverage	0.08737864077669903
v2_split_qwen	1003	nugget_coverage_weighted	0.15384615384615385
v2_split_qwen	1003	f1	0.1460446247464503
v2_split_qwen	1003	f1_weighted	0.2285714285714286
v2_split_qwen	1005	sentences	8.0
v2_split_qwen	1005	character_count	1206.0
v2_split_qwen	1005	sentences_with_citations_or_requiring_citations	8.0
v2_split_qwen	1005	correctly_cited_sentences	2.0
v2_split_qwen	1005	nuggets	111.0
v2_split_qwen	1005	nuggets_weighted	32.0
v2_split_qwen	1005	correct_nuggets	6.0
v2_split_qwen	1005	correct_nuggets_weighted	4.0
v2_split_qwen	1005	citations	29.0
v2_split_qwen	1005	relevant_citations	11.0
v2_split_qwen	1005	supporting_citations	10.0
v2_split_qwen	1005	citation_relevance	0.3793103448275862
v2_split_qwen	1005	citation_support	0.3448275862068966
v2_split_qwen	1005	sentence_support	0.25
v2_split_qwen	1005	nugget_coverage	0.05405405405405406
v2_split_qwen	1005	nugget_coverage_weighted	0.125
v2_split_qwen	1005	f1	0.08888888888888889
v2_split_qwen	1005	f1_weighted	0.16666666666666666
v2_split_qwen	1007	sentences	8.0
v2_split_qwen	1007	character_count	987.0
v2_split_qwen	1007	sentences_with_citations_or_requiring_citations	8.0
v2_split_qwen	1007	correctly_cited_sentences	0.0
v2_split_qwen	1007	nuggets	22.0
v2_split_qwen	1007	nuggets_weighted	6.0
v2_split_qwen	1007	correct_nuggets	4.0
v2_split_qwen	1007	correct_nuggets_weighted	0.0
v2_split_qwen	1007	citations	8.0
v2_split_qwen	1007	relevant_citations	0.0
v2_split_qwen	1007	supporting_citations	0.0
v2_split_qwen	1007	citation_relevance	0.0
v2_split_qwen	1007	citation_support	0.0
v2_split_qwen	1007	sentence_support	0.0
v2_split_qwen	1007	nugget_coverage	0.18181818181818182
v2_split_qwen	1007	nugget_coverage_weighted	0.0
v2_split_qwen	1007	f1	0.0
v2_split_qwen	1007	f1_weighted	0.0
v2_split_qwen	1009	sentences	4.0
v2_split_qwen	1009	character_count	967.0
v2_split_qwen	1009	sentences_with_citations_or_requiring_citations	4.0
v2_split_qwen	1009	correctly_cited_sentences	0.0
v2_split_qwen	1009	nuggets	15.0
v2_split_qwen	1009	nuggets_weighted	8.0
v2_split_qwen	1009	correct_nuggets	4.0
v2_split_qwen	1009	correct_nuggets_weighted	2.0
v2_split_qwen	1009	citations	6.0
v2_split_qwen	1009	relevant_citations	0.0
v2_split_qwen	1009	supporting_citations	0.0
v2_split_qwen	1009	citation_relevance	0.0
v2_split_qwen	1009	citation_support	0.0
v2_split_qwen	1009	sentence_support	0.0
v2_split_qwen	1009	nugget_coverage	0.26666666666666666
v2_split_qwen	1009	nugget_coverage_weighted	0.25
v2_split_qwen	1009	f1	0.0
v2_split_qwen	1009	f1_weighted	0.0
v2_split_qwen	1011	sentences	6.0
v2_split_qwen	1011	character_count	1050.0
v2_split_qwen	1011	sentences_with_citations_or_requiring_citations	6.0
v2_split_qwen	1011	correctly_cited_sentences	2.0
v2_split_qwen	1011	nuggets	63.0
v2_split_qwen	1011	nuggets_weighted	40.0
v2_split_qwen	1011	correct_nuggets	11.0
v2_split_qwen	1011	correct_nuggets_weighted	4.0
v2_split_qwen	1011	citations	41.0
v2_split_qwen	1011	relevant_citations	2.0
v2_split_qwen	1011	supporting_citations	26.0
v2_split_qwen	1011	citation_relevance	0.04878048780487805
v2_split_qwen	1011	citation_support	0.6341463414634146
v2_split_qwen	1011	sentence_support	0.3333333333333333
v2_split_qwen	1011	nugget_coverage	0.1746031746031746
v2_split_qwen	1011	nugget_coverage_weighted	0.1
v2_split_qwen	1011	f1	0.22916666666666666
v2_split_qwen	1011	f1_weighted	0.15384615384615383
v2_split_qwen	1013	sentences	8.0
v2_split_qwen	1013	character_count	1151.0
v2_split_qwen	1013	sentences_with_citations_or_requiring_citations	8.0
v2_split_qwen	1013	correctly_cited_sentences	2.0
v2_split_qwen	1013	nuggets	26.0
v2_split_qwen	1013	nuggets_weighted	12.0
v2_split_qwen	1013	correct_nuggets	8.0
v2_split_qwen	1013	correct_nuggets_weighted	4.0
v2_split_qwen	1013	citations	8.0
v2_split_qwen	1013	relevant_citations	0.0
v2_split_qwen	1013	supporting_citations	2.0
v2_split_qwen	1013	citation_relevance	0.0
v2_split_qwen	1013	citation_support	0.25
v2_split_qwen	1013	sentence_support	0.25
v2_split_qwen	1013	nugget_coverage	0.3076923076923077
v2_split_qwen	1013	nugget_coverage_weighted	0.3333333333333333
v2_split_qwen	1013	f1	0.27586206896551724
v2_split_qwen	1013	f1_weighted	0.28571428571428575
v2_split_qwen	1017	sentences	5.0
v2_split_qwen	1017	character_count	873.0
v2_split_qwen	1017	sentences_with_citations_or_requiring_citations	5.0
v2_split_qwen	1017	correctly_cited_sentences	1.0
v2_split_qwen	1017	nuggets	109.0
v2_split_qwen	1017	nuggets_weighted	62.0
v2_split_qwen	1017	correct_nuggets	8.0
v2_split_qwen	1017	correct_nuggets_weighted	6.0
v2_split_qwen	1017	citations	17.0
v2_split_qwen	1017	relevant_citations	9.0
v2_split_qwen	1017	supporting_citations	1.0
v2_split_qwen	1017	citation_relevance	0.5294117647058824
v2_split_qwen	1017	citation_support	0.058823529411764705
v2_split_qwen	1017	sentence_support	0.2
v2_split_qwen	1017	nugget_coverage	0.07339449541284404
v2_split_qwen	1017	nugget_coverage_weighted	0.0967741935483871
v2_split_qwen	1017	f1	0.10738255033557047
v2_split_qwen	1017	f1_weighted	0.13043478260869568
v2_split_qwen	1025	sentences	7.0
v2_split_qwen	1025	character_count	1157.0
v2_split_qwen	1025	sentences_with_citations_or_requiring_citations	7.0
v2_split_qwen	1025	correctly_cited_sentences	1.0
v2_split_qwen	1025	nuggets	12.0
v2_split_qwen	1025	nuggets_weighted	20.0
v2_split_qwen	1025	correct_nuggets	7.0
v2_split_qwen	1025	correct_nuggets_weighted	10.0
v2_split_qwen	1025	citations	24.0
v2_split_qwen	1025	relevant_citations	5.0
v2_split_qwen	1025	supporting_citations	8.0
v2_split_qwen	1025	citation_relevance	0.20833333333333334
v2_split_qwen	1025	citation_support	0.3333333333333333
v2_split_qwen	1025	sentence_support	0.14285714285714285
v2_split_qwen	1025	nugget_coverage	0.5833333333333334
v2_split_qwen	1025	nugget_coverage_weighted	0.5
v2_split_qwen	1025	f1	0.22950819672131142
v2_split_qwen	1025	f1_weighted	0.22222222222222224
v2_split_qwen	1027	sentences	7.0
v2_split_qwen	1027	character_count	1160.0
v2_split_qwen	1027	sentences_with_citations_or_requiring_citations	7.0
v2_split_qwen	1027	correctly_cited_sentences	0.0
v2_split_qwen	1027	nuggets	7.0
v2_split_qwen	1027	nuggets_weighted	10.0
v2_split_qwen	1027	correct_nuggets	4.0
v2_split_qwen	1027	correct_nuggets_weighted	6.0
v2_split_qwen	1027	citations	19.0
v2_split_qwen	1027	relevant_citations	1.0
v2_split_qwen	1027	supporting_citations	5.0
v2_split_qwen	1027	citation_relevance	0.05263157894736842
v2_split_qwen	1027	citation_support	0.2631578947368421
v2_split_qwen	1027	sentence_support	0.0
v2_split_qwen	1027	nugget_coverage	0.5714285714285714
v2_split_qwen	1027	nugget_coverage_weighted	0.6
v2_split_qwen	1027	f1	0.0
v2_split_qwen	1027	f1_weighted	0.0
v2_split_qwen	1029	sentences	10.0
v2_split_qwen	1029	character_count	1081.0
v2_split_qwen	1029	sentences_with_citations_or_requiring_citations	10.0
v2_split_qwen	1029	correctly_cited_sentences	2.0
v2_split_qwen	1029	nuggets	106.0
v2_split_qwen	1029	nuggets_weighted	58.0
v2_split_qwen	1029	correct_nuggets	6.0
v2_split_qwen	1029	correct_nuggets_weighted	8.0
v2_split_qwen	1029	citations	10.0
v2_split_qwen	1029	relevant_citations	2.0
v2_split_qwen	1029	supporting_citations	2.0
v2_split_qwen	1029	citation_relevance	0.2
v2_split_qwen	1029	citation_support	0.2
v2_split_qwen	1029	sentence_support	0.2
v2_split_qwen	1029	nugget_coverage	0.05660377358490566
v2_split_qwen	1029	nugget_coverage_weighted	0.13793103448275862
v2_split_qwen	1029	f1	0.08823529411764706
v2_split_qwen	1029	f1_weighted	0.16326530612244897
v2_split_qwen	1033	sentences	3.0
v2_split_qwen	1033	character_count	1024.0
v2_split_qwen	1033	sentences_with_citations_or_requiring_citations	3.0
v2_split_qwen	1033	correctly_cited_sentences	0.0
v2_split_qwen	1033	nuggets	56.0
v2_split_qwen	1033	nuggets_weighted	28.0
v2_split_qwen	1033	correct_nuggets	5.0
v2_split_qwen	1033	correct_nuggets_weighted	2.0
v2_split_qwen	1033	citations	24.0
v2_split_qwen	1033	relevant_citations	3.0
v2_split_qwen	1033	supporting_citations	10.0
v2_split_qwen	1033	citation_relevance	0.125
v2_split_qwen	1033	citation_support	0.4166666666666667
v2_split_qwen	1033	sentence_support	0.0
v2_split_qwen	1033	nugget_coverage	0.08928571428571429
v2_split_qwen	1033	nugget_coverage_weighted	0.07142857142857142
v2_split_qwen	1033	f1	0.0
v2_split_qwen	1033	f1_weighted	0.0
v2_split_qwen	1041	sentences	5.0
v2_split_qwen	1041	character_count	1158.0
v2_split_qwen	1041	sentences_with_citations_or_requiring_citations	5.0
v2_split_qwen	1041	correctly_cited_sentences	2.0
v2_split_qwen	1041	nuggets	22.0
v2_split_qwen	1041	nuggets_weighted	10.0
v2_split_qwen	1041	correct_nuggets	4.0
v2_split_qwen	1041	correct_nuggets_weighted	0.0
v2_split_qwen	1041	citations	10.0
v2_split_qwen	1041	relevant_citations	0.0
v2_split_qwen	1041	supporting_citations	6.0
v2_split_qwen	1041	citation_relevance	0.0
v2_split_qwen	1041	citation_support	0.6
v2_split_qwen	1041	sentence_support	0.4
v2_split_qwen	1041	nugget_coverage	0.18181818181818182
v2_split_qwen	1041	nugget_coverage_weighted	0.0
v2_split_qwen	1041	f1	0.25000000000000006
v2_split_qwen	1041	f1_weighted	0.0
v2_split_qwen	1053	sentences	6.0
v2_split_qwen	1053	character_count	1114.0
v2_split_qwen	1053	sentences_with_citations_or_requiring_citations	6.0
v2_split_qwen	1053	correctly_cited_sentences	0.0
v2_split_qwen	1053	nuggets	21.0
v2_split_qwen	1053	nuggets_weighted	14.0
v2_split_qwen	1053	correct_nuggets	3.0
v2_split_qwen	1053	correct_nuggets_weighted	2.0
v2_split_qwen	1053	citations	7.0
v2_split_qwen	1053	relevant_citations	0.0
v2_split_qwen	1053	supporting_citations	1.0
v2_split_qwen	1053	citation_relevance	0.0
v2_split_qwen	1053	citation_support	0.14285714285714285
v2_split_qwen	1053	sentence_support	0.0
v2_split_qwen	1053	nugget_coverage	0.14285714285714285
v2_split_qwen	1053	nugget_coverage_weighted	0.14285714285714285
v2_split_qwen	1053	f1	0.0
v2_split_qwen	1053	f1_weighted	0.0
v2_split_qwen	1065	sentences	7.0
v2_split_qwen	1065	character_count	931.0
v2_split_qwen	1065	sentences_with_citations_or_requiring_citations	7.0
v2_split_qwen	1065	correctly_cited_sentences	0.0
v2_split_qwen	1065	nuggets	30.0
v2_split_qwen	1065	nuggets_weighted	30.0
v2_split_qwen	1065	correct_nuggets	4.0
v2_split_qwen	1065	correct_nuggets_weighted	4.0
v2_split_qwen	1065	citations	8.0
v2_split_qwen	1065	relevant_citations	0.0
v2_split_qwen	1065	supporting_citations	0.0
v2_split_qwen	1065	citation_relevance	0.0
v2_split_qwen	1065	citation_support	0.0
v2_split_qwen	1065	sentence_support	0.0
v2_split_qwen	1065	nugget_coverage	0.13333333333333333
v2_split_qwen	1065	nugget_coverage_weighted	0.13333333333333333
v2_split_qwen	1065	f1	0.0
v2_split_qwen	1065	f1_weighted	0.0
v2_split_qwen	1069	sentences	6.0
v2_split_qwen	1069	character_count	1116.0
v2_split_qwen	1069	sentences_with_citations_or_requiring_citations	6.0
v2_split_qwen	1069	correctly_cited_sentences	0.0
v2_split_qwen	1069	nuggets	11.0
v2_split_qwen	1069	nuggets_weighted	11.0
v2_split_qwen	1069	correct_nuggets	0.0
v2_split_qwen	1069	correct_nuggets_weighted	0.0
v2_split_qwen	1069	citations	6.0
v2_split_qwen	1069	relevant_citations	0.0
v2_split_qwen	1069	supporting_citations	0.0
v2_split_qwen	1069	citation_relevance	0.0
v2_split_qwen	1069	citation_support	0.0
v2_split_qwen	1069	sentence_support	0.0
v2_split_qwen	1069	nugget_coverage	0.0
v2_split_qwen	1069	nugget_coverage_weighted	0.0
v2_split_qwen	1069	f1	0.0
v2_split_qwen	1069	f1_weighted	0.0
