run_id	request_id	metric	value
gptr_ka_q3d3_mt	all	sentences	140.0
gptr_ka_q3d3_mt	all	sentences_with_citations_or_requiring_citations	138.0
gptr_ka_q3d3_mt	all	correctly_cited_sentences	114.0
gptr_ka_q3d3_mt	all	first_instance_sentences_missing_citation	3.0
gptr_ka_q3d3_mt	all	nuggets	815.0
gptr_ka_q3d3_mt	all	nuggets_weighted	477.0
gptr_ka_q3d3_mt	all	correct_nuggets	204.0
gptr_ka_q3d3_mt	all	correct_nuggets_weighted	152.0
gptr_ka_q3d3_mt	all	citations	135.0
gptr_ka_q3d3_mt	all	relevant_citations	67.0
gptr_ka_q3d3_mt	all	supporting_citations	114.0
gptr_ka_q3d3_mt	all	character_count_median	1575.0
gptr_ka_q3d3_mt	all	character_count_max	1801.0
gptr_ka_q3d3_mt	all	citation_relevance_micro	0.4962962962962963
gptr_ka_q3d3_mt	all	citation_relevance_macro	0.503249007936508
gptr_ka_q3d3_mt	all	citation_support_micro	0.8444444444444444
gptr_ka_q3d3_mt	all	citation_support_macro	0.8482638888888889
gptr_ka_q3d3_mt	all	sentence_support_micro	0.8260869565217391
gptr_ka_q3d3_mt	all	sentence_support_macro	0.8345486111111111
gptr_ka_q3d3_mt	all	nugget_coverage_micro	0.25030674846625767
gptr_ka_q3d3_mt	all	nugget_coverage_macro	0.32931727231373054
gptr_ka_q3d3_mt	all	nugget_coverage_weighted_micro	0.31865828092243187
gptr_ka_q3d3_mt	all	nugget_coverage_weighted_macro	0.3210111255656653
gptr_ka_q3d3_mt	all	f1_micro	0.384199831491302
gptr_ka_q3d3_mt	all	f1_macro	0.4383860154744262
gptr_ka_q3d3_mt	all	f1_weighted_micro	0.4599092284417549
gptr_ka_q3d3_mt	all	f1_weighted_macro	0.41419658526491077
gptr_ka_q3d3_mt	1001	sentences	9.0
gptr_ka_q3d3_mt	1001	character_count	1801.0
gptr_ka_q3d3_mt	1001	sentences_with_citations_or_requiring_citations	9.0
gptr_ka_q3d3_mt	1001	correctly_cited_sentences	9.0
gptr_ka_q3d3_mt	1001	nuggets	101.0
gptr_ka_q3d3_mt	1001	nuggets_weighted	110.0
gptr_ka_q3d3_mt	1001	correct_nuggets	39.0
gptr_ka_q3d3_mt	1001	correct_nuggets_weighted	50.0
gptr_ka_q3d3_mt	1001	citations	9.0
gptr_ka_q3d3_mt	1001	relevant_citations	1.0
gptr_ka_q3d3_mt	1001	supporting_citations	9.0
gptr_ka_q3d3_mt	1001	citation_relevance	0.1111111111111111
gptr_ka_q3d3_mt	1001	citation_support	1.0
gptr_ka_q3d3_mt	1001	sentence_support	1.0
gptr_ka_q3d3_mt	1001	nugget_coverage	0.38613861386138615
gptr_ka_q3d3_mt	1001	nugget_coverage_weighted	0.45454545454545453
gptr_ka_q3d3_mt	1001	f1	0.5571428571428572
gptr_ka_q3d3_mt	1001	f1_weighted	0.625
gptr_ka_q3d3_mt	1003	sentences	9.0
gptr_ka_q3d3_mt	1003	character_count	1611.0
gptr_ka_q3d3_mt	1003	sentences_with_citations_or_requiring_citations	7.0
gptr_ka_q3d3_mt	1003	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1003	nuggets	103.0
gptr_ka_q3d3_mt	1003	nuggets_weighted	26.0
gptr_ka_q3d3_mt	1003	correct_nuggets	13.0
gptr_ka_q3d3_mt	1003	correct_nuggets_weighted	2.0
gptr_ka_q3d3_mt	1003	citations	7.0
gptr_ka_q3d3_mt	1003	relevant_citations	3.0
gptr_ka_q3d3_mt	1003	supporting_citations	7.0
gptr_ka_q3d3_mt	1003	citation_relevance	0.42857142857142855
gptr_ka_q3d3_mt	1003	citation_support	1.0
gptr_ka_q3d3_mt	1003	sentence_support	1.0
gptr_ka_q3d3_mt	1003	nugget_coverage	0.1262135922330097
gptr_ka_q3d3_mt	1003	nugget_coverage_weighted	0.07692307692307693
gptr_ka_q3d3_mt	1003	f1	0.22413793103448276
gptr_ka_q3d3_mt	1003	f1_weighted	0.14285714285714288
gptr_ka_q3d3_mt	1005	sentences	10.0
gptr_ka_q3d3_mt	1005	character_count	1774.0
gptr_ka_q3d3_mt	1005	sentences_with_citations_or_requiring_citations	10.0
gptr_ka_q3d3_mt	1005	correctly_cited_sentences	10.0
gptr_ka_q3d3_mt	1005	nuggets	111.0
gptr_ka_q3d3_mt	1005	nuggets_weighted	32.0
gptr_ka_q3d3_mt	1005	correct_nuggets	22.0
gptr_ka_q3d3_mt	1005	correct_nuggets_weighted	2.0
gptr_ka_q3d3_mt	1005	citations	10.0
gptr_ka_q3d3_mt	1005	relevant_citations	5.0
gptr_ka_q3d3_mt	1005	supporting_citations	10.0
gptr_ka_q3d3_mt	1005	citation_relevance	0.5
gptr_ka_q3d3_mt	1005	citation_support	1.0
gptr_ka_q3d3_mt	1005	sentence_support	1.0
gptr_ka_q3d3_mt	1005	nugget_coverage	0.1981981981981982
gptr_ka_q3d3_mt	1005	nugget_coverage_weighted	0.0625
gptr_ka_q3d3_mt	1005	f1	0.33082706766917297
gptr_ka_q3d3_mt	1005	f1_weighted	0.11764705882352941
gptr_ka_q3d3_mt	1007	sentences	9.0
gptr_ka_q3d3_mt	1007	character_count	1340.0
gptr_ka_q3d3_mt	1007	sentences_with_citations_or_requiring_citations	9.0
gptr_ka_q3d3_mt	1007	correctly_cited_sentences	2.0
gptr_ka_q3d3_mt	1007	first_instance_sentences_missing_citation	1.0
gptr_ka_q3d3_mt	1007	nuggets	22.0
gptr_ka_q3d3_mt	1007	nuggets_weighted	6.0
gptr_ka_q3d3_mt	1007	correct_nuggets	8.0
gptr_ka_q3d3_mt	1007	correct_nuggets_weighted	0.0
gptr_ka_q3d3_mt	1007	citations	8.0
gptr_ka_q3d3_mt	1007	relevant_citations	6.0
gptr_ka_q3d3_mt	1007	supporting_citations	2.0
gptr_ka_q3d3_mt	1007	citation_relevance	0.75
gptr_ka_q3d3_mt	1007	citation_support	0.25
gptr_ka_q3d3_mt	1007	sentence_support	0.2222222222222222
gptr_ka_q3d3_mt	1007	nugget_coverage	0.36363636363636365
gptr_ka_q3d3_mt	1007	nugget_coverage_weighted	0.0
gptr_ka_q3d3_mt	1007	f1	0.27586206896551724
gptr_ka_q3d3_mt	1007	f1_weighted	0.0
gptr_ka_q3d3_mt	1009	sentences	9.0
gptr_ka_q3d3_mt	1009	character_count	1411.0
gptr_ka_q3d3_mt	1009	sentences_with_citations_or_requiring_citations	9.0
gptr_ka_q3d3_mt	1009	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1009	nuggets	15.0
gptr_ka_q3d3_mt	1009	nuggets_weighted	8.0
gptr_ka_q3d3_mt	1009	correct_nuggets	8.0
gptr_ka_q3d3_mt	1009	correct_nuggets_weighted	4.0
gptr_ka_q3d3_mt	1009	citations	9.0
gptr_ka_q3d3_mt	1009	relevant_citations	8.0
gptr_ka_q3d3_mt	1009	supporting_citations	7.0
gptr_ka_q3d3_mt	1009	citation_relevance	0.8888888888888888
gptr_ka_q3d3_mt	1009	citation_support	0.7777777777777778
gptr_ka_q3d3_mt	1009	sentence_support	0.7777777777777778
gptr_ka_q3d3_mt	1009	nugget_coverage	0.5333333333333333
gptr_ka_q3d3_mt	1009	nugget_coverage_weighted	0.5
gptr_ka_q3d3_mt	1009	f1	0.6327683615819208
gptr_ka_q3d3_mt	1009	f1_weighted	0.6086956521739131
gptr_ka_q3d3_mt	1011	sentences	10.0
gptr_ka_q3d3_mt	1011	character_count	1668.0
gptr_ka_q3d3_mt	1011	sentences_with_citations_or_requiring_citations	10.0
gptr_ka_q3d3_mt	1011	correctly_cited_sentences	6.0
gptr_ka_q3d3_mt	1011	first_instance_sentences_missing_citation	1.0
gptr_ka_q3d3_mt	1011	nuggets	63.0
gptr_ka_q3d3_mt	1011	nuggets_weighted	40.0
gptr_ka_q3d3_mt	1011	correct_nuggets	18.0
gptr_ka_q3d3_mt	1011	correct_nuggets_weighted	12.0
gptr_ka_q3d3_mt	1011	citations	9.0
gptr_ka_q3d3_mt	1011	relevant_citations	0.0
gptr_ka_q3d3_mt	1011	supporting_citations	6.0
gptr_ka_q3d3_mt	1011	citation_relevance	0.0
gptr_ka_q3d3_mt	1011	citation_support	0.6666666666666666
gptr_ka_q3d3_mt	1011	sentence_support	0.6
gptr_ka_q3d3_mt	1011	nugget_coverage	0.2857142857142857
gptr_ka_q3d3_mt	1011	nugget_coverage_weighted	0.3
gptr_ka_q3d3_mt	1011	f1	0.3870967741935483
gptr_ka_q3d3_mt	1011	f1_weighted	0.4
gptr_ka_q3d3_mt	1013	sentences	9.0
gptr_ka_q3d3_mt	1013	character_count	1491.0
gptr_ka_q3d3_mt	1013	sentences_with_citations_or_requiring_citations	9.0
gptr_ka_q3d3_mt	1013	correctly_cited_sentences	9.0
gptr_ka_q3d3_mt	1013	nuggets	26.0
gptr_ka_q3d3_mt	1013	nuggets_weighted	12.0
gptr_ka_q3d3_mt	1013	correct_nuggets	14.0
gptr_ka_q3d3_mt	1013	correct_nuggets_weighted	10.0
gptr_ka_q3d3_mt	1013	citations	9.0
gptr_ka_q3d3_mt	1013	relevant_citations	5.0
gptr_ka_q3d3_mt	1013	supporting_citations	9.0
gptr_ka_q3d3_mt	1013	citation_relevance	0.5555555555555556
gptr_ka_q3d3_mt	1013	citation_support	1.0
gptr_ka_q3d3_mt	1013	sentence_support	1.0
gptr_ka_q3d3_mt	1013	nugget_coverage	0.5384615384615384
gptr_ka_q3d3_mt	1013	nugget_coverage_weighted	0.8333333333333334
gptr_ka_q3d3_mt	1013	f1	0.7000000000000001
gptr_ka_q3d3_mt	1013	f1_weighted	0.9090909090909091
gptr_ka_q3d3_mt	1017	sentences	8.0
gptr_ka_q3d3_mt	1017	character_count	1487.0
gptr_ka_q3d3_mt	1017	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1017	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1017	nuggets	109.0
gptr_ka_q3d3_mt	1017	nuggets_weighted	62.0
gptr_ka_q3d3_mt	1017	correct_nuggets	26.0
gptr_ka_q3d3_mt	1017	correct_nuggets_weighted	24.0
gptr_ka_q3d3_mt	1017	citations	8.0
gptr_ka_q3d3_mt	1017	relevant_citations	7.0
gptr_ka_q3d3_mt	1017	supporting_citations	7.0
gptr_ka_q3d3_mt	1017	citation_relevance	0.875
gptr_ka_q3d3_mt	1017	citation_support	0.875
gptr_ka_q3d3_mt	1017	sentence_support	0.875
gptr_ka_q3d3_mt	1017	nugget_coverage	0.23853211009174313
gptr_ka_q3d3_mt	1017	nugget_coverage_weighted	0.3870967741935484
gptr_ka_q3d3_mt	1017	f1	0.3748712667353245
gptr_ka_q3d3_mt	1017	f1_weighted	0.5367412140575079
gptr_ka_q3d3_mt	1025	sentences	8.0
gptr_ka_q3d3_mt	1025	character_count	1679.0
gptr_ka_q3d3_mt	1025	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1025	correctly_cited_sentences	8.0
gptr_ka_q3d3_mt	1025	nuggets	12.0
gptr_ka_q3d3_mt	1025	nuggets_weighted	20.0
gptr_ka_q3d3_mt	1025	correct_nuggets	8.0
gptr_ka_q3d3_mt	1025	correct_nuggets_weighted	12.0
gptr_ka_q3d3_mt	1025	citations	8.0
gptr_ka_q3d3_mt	1025	relevant_citations	5.0
gptr_ka_q3d3_mt	1025	supporting_citations	8.0
gptr_ka_q3d3_mt	1025	citation_relevance	0.625
gptr_ka_q3d3_mt	1025	citation_support	1.0
gptr_ka_q3d3_mt	1025	sentence_support	1.0
gptr_ka_q3d3_mt	1025	nugget_coverage	0.6666666666666666
gptr_ka_q3d3_mt	1025	nugget_coverage_weighted	0.6
gptr_ka_q3d3_mt	1025	f1	0.8
gptr_ka_q3d3_mt	1025	f1_weighted	0.7499999999999999
gptr_ka_q3d3_mt	1027	sentences	8.0
gptr_ka_q3d3_mt	1027	character_count	1416.0
gptr_ka_q3d3_mt	1027	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1027	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1027	first_instance_sentences_missing_citation	1.0
gptr_ka_q3d3_mt	1027	nuggets	7.0
gptr_ka_q3d3_mt	1027	nuggets_weighted	10.0
gptr_ka_q3d3_mt	1027	correct_nuggets	4.0
gptr_ka_q3d3_mt	1027	correct_nuggets_weighted	6.0
gptr_ka_q3d3_mt	1027	citations	7.0
gptr_ka_q3d3_mt	1027	relevant_citations	1.0
gptr_ka_q3d3_mt	1027	supporting_citations	7.0
gptr_ka_q3d3_mt	1027	citation_relevance	0.14285714285714285
gptr_ka_q3d3_mt	1027	citation_support	1.0
gptr_ka_q3d3_mt	1027	sentence_support	0.875
gptr_ka_q3d3_mt	1027	nugget_coverage	0.5714285714285714
gptr_ka_q3d3_mt	1027	nugget_coverage_weighted	0.6
gptr_ka_q3d3_mt	1027	f1	0.691358024691358
gptr_ka_q3d3_mt	1027	f1_weighted	0.711864406779661
gptr_ka_q3d3_mt	1029	sentences	8.0
gptr_ka_q3d3_mt	1029	character_count	1676.0
gptr_ka_q3d3_mt	1029	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1029	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1029	nuggets	106.0
gptr_ka_q3d3_mt	1029	nuggets_weighted	58.0
gptr_ka_q3d3_mt	1029	correct_nuggets	8.0
gptr_ka_q3d3_mt	1029	correct_nuggets_weighted	4.0
gptr_ka_q3d3_mt	1029	citations	8.0
gptr_ka_q3d3_mt	1029	relevant_citations	8.0
gptr_ka_q3d3_mt	1029	supporting_citations	7.0
gptr_ka_q3d3_mt	1029	citation_relevance	1.0
gptr_ka_q3d3_mt	1029	citation_support	0.875
gptr_ka_q3d3_mt	1029	sentence_support	0.875
gptr_ka_q3d3_mt	1029	nugget_coverage	0.07547169811320754
gptr_ka_q3d3_mt	1029	nugget_coverage_weighted	0.06896551724137931
gptr_ka_q3d3_mt	1029	f1	0.13895781637717122
gptr_ka_q3d3_mt	1029	f1_weighted	0.1278538812785388
gptr_ka_q3d3_mt	1033	sentences	8.0
gptr_ka_q3d3_mt	1033	character_count	1516.0
gptr_ka_q3d3_mt	1033	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1033	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1033	nuggets	56.0
gptr_ka_q3d3_mt	1033	nuggets_weighted	28.0
gptr_ka_q3d3_mt	1033	correct_nuggets	12.0
gptr_ka_q3d3_mt	1033	correct_nuggets_weighted	10.0
gptr_ka_q3d3_mt	1033	citations	8.0
gptr_ka_q3d3_mt	1033	relevant_citations	5.0
gptr_ka_q3d3_mt	1033	supporting_citations	7.0
gptr_ka_q3d3_mt	1033	citation_relevance	0.625
gptr_ka_q3d3_mt	1033	citation_support	0.875
gptr_ka_q3d3_mt	1033	sentence_support	0.875
gptr_ka_q3d3_mt	1033	nugget_coverage	0.21428571428571427
gptr_ka_q3d3_mt	1033	nugget_coverage_weighted	0.35714285714285715
gptr_ka_q3d3_mt	1033	f1	0.34426229508196726
gptr_ka_q3d3_mt	1033	f1_weighted	0.5072463768115941
gptr_ka_q3d3_mt	1041	sentences	8.0
gptr_ka_q3d3_mt	1041	character_count	1694.0
gptr_ka_q3d3_mt	1041	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1041	correctly_cited_sentences	8.0
gptr_ka_q3d3_mt	1041	nuggets	22.0
gptr_ka_q3d3_mt	1041	nuggets_weighted	10.0
gptr_ka_q3d3_mt	1041	correct_nuggets	7.0
gptr_ka_q3d3_mt	1041	correct_nuggets_weighted	0.0
gptr_ka_q3d3_mt	1041	citations	8.0
gptr_ka_q3d3_mt	1041	relevant_citations	4.0
gptr_ka_q3d3_mt	1041	supporting_citations	8.0
gptr_ka_q3d3_mt	1041	citation_relevance	0.5
gptr_ka_q3d3_mt	1041	citation_support	1.0
gptr_ka_q3d3_mt	1041	sentence_support	1.0
gptr_ka_q3d3_mt	1041	nugget_coverage	0.3181818181818182
gptr_ka_q3d3_mt	1041	nugget_coverage_weighted	0.0
gptr_ka_q3d3_mt	1041	f1	0.4827586206896552
gptr_ka_q3d3_mt	1041	f1_weighted	0.0
gptr_ka_q3d3_mt	1053	sentences	8.0
gptr_ka_q3d3_mt	1053	character_count	1573.0
gptr_ka_q3d3_mt	1053	sentences_with_citations_or_requiring_citations	8.0
gptr_ka_q3d3_mt	1053	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1053	nuggets	21.0
gptr_ka_q3d3_mt	1053	nuggets_weighted	14.0
gptr_ka_q3d3_mt	1053	correct_nuggets	9.0
gptr_ka_q3d3_mt	1053	correct_nuggets_weighted	8.0
gptr_ka_q3d3_mt	1053	citations	8.0
gptr_ka_q3d3_mt	1053	relevant_citations	6.0
gptr_ka_q3d3_mt	1053	supporting_citations	7.0
gptr_ka_q3d3_mt	1053	citation_relevance	0.75
gptr_ka_q3d3_mt	1053	citation_support	0.875
gptr_ka_q3d3_mt	1053	sentence_support	0.875
gptr_ka_q3d3_mt	1053	nugget_coverage	0.42857142857142855
gptr_ka_q3d3_mt	1053	nugget_coverage_weighted	0.5714285714285714
gptr_ka_q3d3_mt	1053	f1	0.5753424657534246
gptr_ka_q3d3_mt	1053	f1_weighted	0.691358024691358
gptr_ka_q3d3_mt	1065	sentences	10.0
gptr_ka_q3d3_mt	1065	character_count	1577.0
gptr_ka_q3d3_mt	1065	sentences_with_citations_or_requiring_citations	10.0
gptr_ka_q3d3_mt	1065	correctly_cited_sentences	6.0
gptr_ka_q3d3_mt	1065	nuggets	30.0
gptr_ka_q3d3_mt	1065	nuggets_weighted	30.0
gptr_ka_q3d3_mt	1065	correct_nuggets	7.0
gptr_ka_q3d3_mt	1065	correct_nuggets_weighted	7.0
gptr_ka_q3d3_mt	1065	citations	10.0
gptr_ka_q3d3_mt	1065	relevant_citations	3.0
gptr_ka_q3d3_mt	1065	supporting_citations	6.0
gptr_ka_q3d3_mt	1065	citation_relevance	0.3
gptr_ka_q3d3_mt	1065	citation_support	0.6
gptr_ka_q3d3_mt	1065	sentence_support	0.6
gptr_ka_q3d3_mt	1065	nugget_coverage	0.23333333333333334
gptr_ka_q3d3_mt	1065	nugget_coverage_weighted	0.23333333333333334
gptr_ka_q3d3_mt	1065	f1	0.336
gptr_ka_q3d3_mt	1065	f1_weighted	0.336
gptr_ka_q3d3_mt	1069	sentences	9.0
gptr_ka_q3d3_mt	1069	character_count	1516.0
gptr_ka_q3d3_mt	1069	sentences_with_citations_or_requiring_citations	9.0
gptr_ka_q3d3_mt	1069	correctly_cited_sentences	7.0
gptr_ka_q3d3_mt	1069	nuggets	11.0
gptr_ka_q3d3_mt	1069	nuggets_weighted	11.0
gptr_ka_q3d3_mt	1069	correct_nuggets	1.0
gptr_ka_q3d3_mt	1069	correct_nuggets_weighted	1.0
gptr_ka_q3d3_mt	1069	citations	9.0
gptr_ka_q3d3_mt	1069	relevant_citations	0.0
gptr_ka_q3d3_mt	1069	supporting_citations	7.0
gptr_ka_q3d3_mt	1069	citation_relevance	0.0
gptr_ka_q3d3_mt	1069	citation_support	0.7777777777777778
gptr_ka_q3d3_mt	1069	sentence_support	0.7777777777777778
gptr_ka_q3d3_mt	1069	nugget_coverage	0.09090909090909091
gptr_ka_q3d3_mt	1069	nugget_coverage_weighted	0.09090909090909091
gptr_ka_q3d3_mt	1069	f1	0.1627906976744186
gptr_ka_q3d3_mt	1069	f1_weighted	0.1627906976744186
