run_id	request_id	metric	value
lg_e2_3q5r3l	all	sentences	246.0
lg_e2_3q5r3l	all	sentences_with_citations_or_requiring_citations	220.0
lg_e2_3q5r3l	all	correctly_cited_sentences	190.0
lg_e2_3q5r3l	all	first_instance_sentences_missing_citation	17.0
lg_e2_3q5r3l	all	nuggets	815.0
lg_e2_3q5r3l	all	nuggets_weighted	477.0
lg_e2_3q5r3l	all	correct_nuggets	238.0
lg_e2_3q5r3l	all	correct_nuggets_weighted	175.0
lg_e2_3q5r3l	all	citations	249.0
lg_e2_3q5r3l	all	relevant_citations	146.0
lg_e2_3q5r3l	all	supporting_citations	235.0
lg_e2_3q5r3l	all	character_count_median	1912.5
lg_e2_3q5r3l	all	character_count_max	2000.0
lg_e2_3q5r3l	all	citation_relevance_micro	0.5863453815261044
lg_e2_3q5r3l	all	citation_relevance_macro	0.6151011778277878
lg_e2_3q5r3l	all	citation_support_micro	0.9437751004016064
lg_e2_3q5r3l	all	citation_support_macro	0.9308276074978661
lg_e2_3q5r3l	all	sentence_support_micro	0.8636363636363636
lg_e2_3q5r3l	all	sentence_support_macro	0.849836695811928
lg_e2_3q5r3l	all	nugget_coverage_micro	0.2920245398773006
lg_e2_3q5r3l	all	nugget_coverage_macro	0.3823507647359701
lg_e2_3q5r3l	all	nugget_coverage_weighted_micro	0.3668763102725367
lg_e2_3q5r3l	all	nugget_coverage_weighted_macro	0.4256966244730427
lg_e2_3q5r3l	all	f1_micro	0.4364654215530138
lg_e2_3q5r3l	all	f1_macro	0.4954766547193512
lg_e2_3q5r3l	all	f1_weighted_micro	0.5149848989390537
lg_e2_3q5r3l	all	f1_weighted_macro	0.5259892759425036
lg_e2_3q5r3l	1001	sentences	15.0
lg_e2_3q5r3l	1001	character_count	1917.0
lg_e2_3q5r3l	1001	sentences_with_citations_or_requiring_citations	15.0
lg_e2_3q5r3l	1001	correctly_cited_sentences	15.0
lg_e2_3q5r3l	1001	nuggets	101.0
lg_e2_3q5r3l	1001	nuggets_weighted	110.0
lg_e2_3q5r3l	1001	correct_nuggets	37.0
lg_e2_3q5r3l	1001	correct_nuggets_weighted	40.0
lg_e2_3q5r3l	1001	citations	18.0
lg_e2_3q5r3l	1001	relevant_citations	12.0
lg_e2_3q5r3l	1001	supporting_citations	18.0
lg_e2_3q5r3l	1001	citation_relevance	0.6666666666666666
lg_e2_3q5r3l	1001	citation_support	1.0
lg_e2_3q5r3l	1001	sentence_support	1.0
lg_e2_3q5r3l	1001	nugget_coverage	0.36633663366336633
lg_e2_3q5r3l	1001	nugget_coverage_weighted	0.36363636363636365
lg_e2_3q5r3l	1001	f1	0.5362318840579711
lg_e2_3q5r3l	1001	f1_weighted	0.5333333333333333
lg_e2_3q5r3l	1003	sentences	16.0
lg_e2_3q5r3l	1003	character_count	1908.0
lg_e2_3q5r3l	1003	sentences_with_citations_or_requiring_citations	14.0
lg_e2_3q5r3l	1003	correctly_cited_sentences	11.0
lg_e2_3q5r3l	1003	first_instance_sentences_missing_citation	1.0
lg_e2_3q5r3l	1003	nuggets	103.0
lg_e2_3q5r3l	1003	nuggets_weighted	26.0
lg_e2_3q5r3l	1003	correct_nuggets	17.0
lg_e2_3q5r3l	1003	correct_nuggets_weighted	4.0
lg_e2_3q5r3l	1003	citations	13.0
lg_e2_3q5r3l	1003	relevant_citations	12.0
lg_e2_3q5r3l	1003	supporting_citations	11.0
lg_e2_3q5r3l	1003	citation_relevance	0.9230769230769231
lg_e2_3q5r3l	1003	citation_support	0.8461538461538461
lg_e2_3q5r3l	1003	sentence_support	0.7857142857142857
lg_e2_3q5r3l	1003	nugget_coverage	0.1650485436893204
lg_e2_3q5r3l	1003	nugget_coverage_weighted	0.15384615384615385
lg_e2_3q5r3l	1003	f1	0.27279358132749815
lg_e2_3q5r3l	1003	f1_weighted	0.2573099415204678
lg_e2_3q5r3l	1005	sentences	18.0
lg_e2_3q5r3l	1005	character_count	2000.0
lg_e2_3q5r3l	1005	sentences_with_citations_or_requiring_citations	17.0
lg_e2_3q5r3l	1005	correctly_cited_sentences	16.0
lg_e2_3q5r3l	1005	first_instance_sentences_missing_citation	1.0
lg_e2_3q5r3l	1005	nuggets	111.0
lg_e2_3q5r3l	1005	nuggets_weighted	32.0
lg_e2_3q5r3l	1005	correct_nuggets	21.0
lg_e2_3q5r3l	1005	correct_nuggets_weighted	8.0
lg_e2_3q5r3l	1005	citations	16.0
lg_e2_3q5r3l	1005	relevant_citations	14.0
lg_e2_3q5r3l	1005	supporting_citations	16.0
lg_e2_3q5r3l	1005	citation_relevance	0.875
lg_e2_3q5r3l	1005	citation_support	1.0
lg_e2_3q5r3l	1005	sentence_support	0.9411764705882353
lg_e2_3q5r3l	1005	nugget_coverage	0.1891891891891892
lg_e2_3q5r3l	1005	nugget_coverage_weighted	0.25
lg_e2_3q5r3l	1005	f1	0.3150492264416315
lg_e2_3q5r3l	1005	f1_weighted	0.3950617283950617
lg_e2_3q5r3l	1007	sentences	18.0
lg_e2_3q5r3l	1007	character_count	1926.0
lg_e2_3q5r3l	1007	sentences_with_citations_or_requiring_citations	17.0
lg_e2_3q5r3l	1007	correctly_cited_sentences	15.0
lg_e2_3q5r3l	1007	first_instance_sentences_missing_citation	1.0
lg_e2_3q5r3l	1007	nuggets	22.0
lg_e2_3q5r3l	1007	nuggets_weighted	6.0
lg_e2_3q5r3l	1007	correct_nuggets	12.0
lg_e2_3q5r3l	1007	correct_nuggets_weighted	2.0
lg_e2_3q5r3l	1007	citations	16.0
lg_e2_3q5r3l	1007	relevant_citations	14.0
lg_e2_3q5r3l	1007	supporting_citations	15.0
lg_e2_3q5r3l	1007	citation_relevance	0.875
lg_e2_3q5r3l	1007	citation_support	0.9375
lg_e2_3q5r3l	1007	sentence_support	0.8823529411764706
lg_e2_3q5r3l	1007	nugget_coverage	0.5454545454545454
lg_e2_3q5r3l	1007	nugget_coverage_weighted	0.3333333333333333
lg_e2_3q5r3l	1007	f1	0.6741573033707865
lg_e2_3q5r3l	1007	f1_weighted	0.48387096774193544
lg_e2_3q5r3l	1009	sentences	19.0
lg_e2_3q5r3l	1009	character_count	2000.0
lg_e2_3q5r3l	1009	sentences_with_citations_or_requiring_citations	19.0
lg_e2_3q5r3l	1009	correctly_cited_sentences	17.0
lg_e2_3q5r3l	1009	first_instance_sentences_missing_citation	2.0
lg_e2_3q5r3l	1009	nuggets	15.0
lg_e2_3q5r3l	1009	nuggets_weighted	8.0
lg_e2_3q5r3l	1009	correct_nuggets	10.0
lg_e2_3q5r3l	1009	correct_nuggets_weighted	6.0
lg_e2_3q5r3l	1009	citations	17.0
lg_e2_3q5r3l	1009	relevant_citations	11.0
lg_e2_3q5r3l	1009	supporting_citations	17.0
lg_e2_3q5r3l	1009	citation_relevance	0.6470588235294118
lg_e2_3q5r3l	1009	citation_support	1.0
lg_e2_3q5r3l	1009	sentence_support	0.8947368421052632
lg_e2_3q5r3l	1009	nugget_coverage	0.6666666666666666
lg_e2_3q5r3l	1009	nugget_coverage_weighted	0.75
lg_e2_3q5r3l	1009	f1	0.7640449438202247
lg_e2_3q5r3l	1009	f1_weighted	0.816
lg_e2_3q5r3l	1011	sentences	13.0
lg_e2_3q5r3l	1011	character_count	1756.0
lg_e2_3q5r3l	1011	sentences_with_citations_or_requiring_citations	13.0
lg_e2_3q5r3l	1011	correctly_cited_sentences	12.0
lg_e2_3q5r3l	1011	nuggets	63.0
lg_e2_3q5r3l	1011	nuggets_weighted	40.0
lg_e2_3q5r3l	1011	correct_nuggets	21.0
lg_e2_3q5r3l	1011	correct_nuggets_weighted	16.0
lg_e2_3q5r3l	1011	citations	16.0
lg_e2_3q5r3l	1011	relevant_citations	1.0
lg_e2_3q5r3l	1011	supporting_citations	15.0
lg_e2_3q5r3l	1011	citation_relevance	0.0625
lg_e2_3q5r3l	1011	citation_support	0.9375
lg_e2_3q5r3l	1011	sentence_support	0.9230769230769231
lg_e2_3q5r3l	1011	nugget_coverage	0.3333333333333333
lg_e2_3q5r3l	1011	nugget_coverage_weighted	0.4
lg_e2_3q5r3l	1011	f1	0.489795918367347
lg_e2_3q5r3l	1011	f1_weighted	0.5581395348837209
lg_e2_3q5r3l	1013	sentences	13.0
lg_e2_3q5r3l	1013	character_count	1608.0
lg_e2_3q5r3l	1013	sentences_with_citations_or_requiring_citations	10.0
lg_e2_3q5r3l	1013	correctly_cited_sentences	9.0
lg_e2_3q5r3l	1013	first_instance_sentences_missing_citation	1.0
lg_e2_3q5r3l	1013	nuggets	26.0
lg_e2_3q5r3l	1013	nuggets_weighted	12.0
lg_e2_3q5r3l	1013	correct_nuggets	13.0
lg_e2_3q5r3l	1013	correct_nuggets_weighted	10.0
lg_e2_3q5r3l	1013	citations	10.0
lg_e2_3q5r3l	1013	relevant_citations	8.0
lg_e2_3q5r3l	1013	supporting_citations	10.0
lg_e2_3q5r3l	1013	citation_relevance	0.8
lg_e2_3q5r3l	1013	citation_support	1.0
lg_e2_3q5r3l	1013	sentence_support	0.9
lg_e2_3q5r3l	1013	nugget_coverage	0.5
lg_e2_3q5r3l	1013	nugget_coverage_weighted	0.8333333333333334
lg_e2_3q5r3l	1013	f1	0.6428571428571429
lg_e2_3q5r3l	1013	f1_weighted	0.8653846153846153
lg_e2_3q5r3l	1017	sentences	15.0
lg_e2_3q5r3l	1017	character_count	1829.0
lg_e2_3q5r3l	1017	sentences_with_citations_or_requiring_citations	9.0
lg_e2_3q5r3l	1017	correctly_cited_sentences	9.0
lg_e2_3q5r3l	1017	nuggets	109.0
lg_e2_3q5r3l	1017	nuggets_weighted	62.0
lg_e2_3q5r3l	1017	correct_nuggets	36.0
lg_e2_3q5r3l	1017	correct_nuggets_weighted	30.0
lg_e2_3q5r3l	1017	citations	10.0
lg_e2_3q5r3l	1017	relevant_citations	10.0
lg_e2_3q5r3l	1017	supporting_citations	10.0
lg_e2_3q5r3l	1017	citation_relevance	1.0
lg_e2_3q5r3l	1017	citation_support	1.0
lg_e2_3q5r3l	1017	sentence_support	1.0
lg_e2_3q5r3l	1017	nugget_coverage	0.3302752293577982
lg_e2_3q5r3l	1017	nugget_coverage_weighted	0.4838709677419355
lg_e2_3q5r3l	1017	f1	0.496551724137931
lg_e2_3q5r3l	1017	f1_weighted	0.6521739130434783
lg_e2_3q5r3l	1025	sentences	16.0
lg_e2_3q5r3l	1025	character_count	2000.0
lg_e2_3q5r3l	1025	sentences_with_citations_or_requiring_citations	15.0
lg_e2_3q5r3l	1025	correctly_cited_sentences	12.0
lg_e2_3q5r3l	1025	nuggets	12.0
lg_e2_3q5r3l	1025	nuggets_weighted	20.0
lg_e2_3q5r3l	1025	correct_nuggets	10.0
lg_e2_3q5r3l	1025	correct_nuggets_weighted	16.0
lg_e2_3q5r3l	1025	citations	27.0
lg_e2_3q5r3l	1025	relevant_citations	7.0
lg_e2_3q5r3l	1025	supporting_citations	24.0
lg_e2_3q5r3l	1025	citation_relevance	0.25925925925925924
lg_e2_3q5r3l	1025	citation_support	0.8888888888888888
lg_e2_3q5r3l	1025	sentence_support	0.8
lg_e2_3q5r3l	1025	nugget_coverage	0.8333333333333334
lg_e2_3q5r3l	1025	nugget_coverage_weighted	0.8
lg_e2_3q5r3l	1025	f1	0.816326530612245
lg_e2_3q5r3l	1025	f1_weighted	0.8000000000000002
lg_e2_3q5r3l	1027	sentences	15.0
lg_e2_3q5r3l	1027	character_count	1987.0
lg_e2_3q5r3l	1027	sentences_with_citations_or_requiring_citations	15.0
lg_e2_3q5r3l	1027	correctly_cited_sentences	14.0
lg_e2_3q5r3l	1027	nuggets	7.0
lg_e2_3q5r3l	1027	nuggets_weighted	10.0
lg_e2_3q5r3l	1027	correct_nuggets	5.0
lg_e2_3q5r3l	1027	correct_nuggets_weighted	8.0
lg_e2_3q5r3l	1027	citations	29.0
lg_e2_3q5r3l	1027	relevant_citations	12.0
lg_e2_3q5r3l	1027	supporting_citations	27.0
lg_e2_3q5r3l	1027	citation_relevance	0.41379310344827586
lg_e2_3q5r3l	1027	citation_support	0.9310344827586207
lg_e2_3q5r3l	1027	sentence_support	0.9333333333333333
lg_e2_3q5r3l	1027	nugget_coverage	0.7142857142857143
lg_e2_3q5r3l	1027	nugget_coverage_weighted	0.8
lg_e2_3q5r3l	1027	f1	0.809248554913295
lg_e2_3q5r3l	1027	f1_weighted	0.8615384615384616
lg_e2_3q5r3l	1029	sentences	14.0
lg_e2_3q5r3l	1029	character_count	1875.0
lg_e2_3q5r3l	1029	sentences_with_citations_or_requiring_citations	14.0
lg_e2_3q5r3l	1029	correctly_cited_sentences	12.0
lg_e2_3q5r3l	1029	first_instance_sentences_missing_citation	1.0
lg_e2_3q5r3l	1029	nuggets	106.0
lg_e2_3q5r3l	1029	nuggets_weighted	58.0
lg_e2_3q5r3l	1029	correct_nuggets	17.0
lg_e2_3q5r3l	1029	correct_nuggets_weighted	8.0
lg_e2_3q5r3l	1029	citations	15.0
lg_e2_3q5r3l	1029	relevant_citations	15.0
lg_e2_3q5r3l	1029	supporting_citations	14.0
lg_e2_3q5r3l	1029	citation_relevance	1.0
lg_e2_3q5r3l	1029	citation_support	0.9333333333333333
lg_e2_3q5r3l	1029	sentence_support	0.8571428571428571
lg_e2_3q5r3l	1029	nugget_coverage	0.16037735849056603
lg_e2_3q5r3l	1029	nugget_coverage_weighted	0.13793103448275862
lg_e2_3q5r3l	1029	f1	0.27019867549668874
lg_e2_3q5r3l	1029	f1_weighted	0.23762376237623764
lg_e2_3q5r3l	1033	sentences	14.0
lg_e2_3q5r3l	1033	character_count	1695.0
lg_e2_3q5r3l	1033	sentences_with_citations_or_requiring_citations	14.0
lg_e2_3q5r3l	1033	correctly_cited_sentences	13.0
lg_e2_3q5r3l	1033	nuggets	56.0
lg_e2_3q5r3l	1033	nuggets_weighted	28.0
lg_e2_3q5r3l	1033	correct_nuggets	19.0
lg_e2_3q5r3l	1033	correct_nuggets_weighted	14.0
lg_e2_3q5r3l	1033	citations	22.0
lg_e2_3q5r3l	1033	relevant_citations	12.0
lg_e2_3q5r3l	1033	supporting_citations	21.0
lg_e2_3q5r3l	1033	citation_relevance	0.5454545454545454
lg_e2_3q5r3l	1033	citation_support	0.9545454545454546
lg_e2_3q5r3l	1033	sentence_support	0.9285714285714286
lg_e2_3q5r3l	1033	nugget_coverage	0.3392857142857143
lg_e2_3q5r3l	1033	nugget_coverage_weighted	0.5
lg_e2_3q5r3l	1033	f1	0.4969818913480886
lg_e2_3q5r3l	1033	f1_weighted	0.65
lg_e2_3q5r3l	1041	sentences	16.0
lg_e2_3q5r3l	1041	character_count	1986.0
lg_e2_3q5r3l	1041	sentences_with_citations_or_requiring_citations	15.0
lg_e2_3q5r3l	1041	correctly_cited_sentences	13.0
lg_e2_3q5r3l	1041	first_instance_sentences_missing_citation	2.0
lg_e2_3q5r3l	1041	nuggets	22.0
lg_e2_3q5r3l	1041	nuggets_weighted	10.0
lg_e2_3q5r3l	1041	correct_nuggets	10.0
lg_e2_3q5r3l	1041	correct_nuggets_weighted	2.0
lg_e2_3q5r3l	1041	citations	14.0
lg_e2_3q5r3l	1041	relevant_citations	5.0
lg_e2_3q5r3l	1041	supporting_citations	14.0
lg_e2_3q5r3l	1041	citation_relevance	0.35714285714285715
lg_e2_3q5r3l	1041	citation_support	1.0
lg_e2_3q5r3l	1041	sentence_support	0.8666666666666667
lg_e2_3q5r3l	1041	nugget_coverage	0.45454545454545453
lg_e2_3q5r3l	1041	nugget_coverage_weighted	0.2
lg_e2_3q5r3l	1041	f1	0.5963302752293578
lg_e2_3q5r3l	1041	f1_weighted	0.325
lg_e2_3q5r3l	1053	sentences	14.0
lg_e2_3q5r3l	1053	character_count	1806.0
lg_e2_3q5r3l	1053	sentences_with_citations_or_requiring_citations	14.0
lg_e2_3q5r3l	1053	correctly_cited_sentences	14.0
lg_e2_3q5r3l	1053	nuggets	21.0
lg_e2_3q5r3l	1053	nuggets_weighted	14.0
lg_e2_3q5r3l	1053	correct_nuggets	9.0
lg_e2_3q5r3l	1053	correct_nuggets_weighted	10.0
lg_e2_3q5r3l	1053	citations	15.0
lg_e2_3q5r3l	1053	relevant_citations	10.0
lg_e2_3q5r3l	1053	supporting_citations	15.0
lg_e2_3q5r3l	1053	citation_relevance	0.6666666666666666
lg_e2_3q5r3l	1053	citation_support	1.0
lg_e2_3q5r3l	1053	sentence_support	1.0
lg_e2_3q5r3l	1053	nugget_coverage	0.42857142857142855
lg_e2_3q5r3l	1053	nugget_coverage_weighted	0.7142857142857143
lg_e2_3q5r3l	1053	f1	0.6
lg_e2_3q5r3l	1053	f1_weighted	0.8333333333333333
lg_e2_3q5r3l	1065	sentences	14.0
lg_e2_3q5r3l	1065	character_count	1731.0
lg_e2_3q5r3l	1065	sentences_with_citations_or_requiring_citations	6.0
lg_e2_3q5r3l	1065	correctly_cited_sentences	3.0
lg_e2_3q5r3l	1065	first_instance_sentences_missing_citation	2.0
lg_e2_3q5r3l	1065	nuggets	30.0
lg_e2_3q5r3l	1065	nuggets_weighted	30.0
lg_e2_3q5r3l	1065	correct_nuggets	0.0
lg_e2_3q5r3l	1065	correct_nuggets_weighted	0.0
lg_e2_3q5r3l	1065	citations	4.0
lg_e2_3q5r3l	1065	relevant_citations	3.0
lg_e2_3q5r3l	1065	supporting_citations	3.0
lg_e2_3q5r3l	1065	citation_relevance	0.75
lg_e2_3q5r3l	1065	citation_support	0.75
lg_e2_3q5r3l	1065	sentence_support	0.5
lg_e2_3q5r3l	1065	nugget_coverage	0.0
lg_e2_3q5r3l	1065	nugget_coverage_weighted	0.0
lg_e2_3q5r3l	1065	f1	0.0
lg_e2_3q5r3l	1065	f1_weighted	0.0
lg_e2_3q5r3l	1069	sentences	16.0
lg_e2_3q5r3l	1069	character_count	1972.0
lg_e2_3q5r3l	1069	sentences_with_citations_or_requiring_citations	13.0
lg_e2_3q5r3l	1069	correctly_cited_sentences	5.0
lg_e2_3q5r3l	1069	first_instance_sentences_missing_citation	6.0
lg_e2_3q5r3l	1069	nuggets	11.0
lg_e2_3q5r3l	1069	nuggets_weighted	11.0
lg_e2_3q5r3l	1069	correct_nuggets	1.0
lg_e2_3q5r3l	1069	correct_nuggets_weighted	1.0
lg_e2_3q5r3l	1069	citations	7.0
lg_e2_3q5r3l	1069	relevant_citations	0.0
lg_e2_3q5r3l	1069	supporting_citations	5.0
lg_e2_3q5r3l	1069	citation_relevance	0.0
lg_e2_3q5r3l	1069	citation_support	0.7142857142857143
lg_e2_3q5r3l	1069	sentence_support	0.38461538461538464
lg_e2_3q5r3l	1069	nugget_coverage	0.09090909090909091
lg_e2_3q5r3l	1069	nugget_coverage_weighted	0.09090909090909091
lg_e2_3q5r3l	1069	f1	0.14705882352941177
lg_e2_3q5r3l	1069	f1_weighted	0.14705882352941177
