run_id	request_id	metric	value
gptr_nt_q4d4_mt	all	sentences	167.0
gptr_nt_q4d4_mt	all	sentences_with_citations_or_requiring_citations	165.0
gptr_nt_q4d4_mt	all	correctly_cited_sentences	136.0
gptr_nt_q4d4_mt	all	first_instance_sentences_missing_citation	1.0
gptr_nt_q4d4_mt	all	nuggets	815.0
gptr_nt_q4d4_mt	all	nuggets_weighted	477.0
gptr_nt_q4d4_mt	all	correct_nuggets	221.0
gptr_nt_q4d4_mt	all	correct_nuggets_weighted	154.0
gptr_nt_q4d4_mt	all	citations	166.0
gptr_nt_q4d4_mt	all	relevant_citations	88.0
gptr_nt_q4d4_mt	all	supporting_citations	137.0
gptr_nt_q4d4_mt	all	character_count_median	1669.5
gptr_nt_q4d4_mt	all	character_count_max	1881.0
gptr_nt_q4d4_mt	all	citation_relevance_micro	0.5301204819277109
gptr_nt_q4d4_mt	all	citation_relevance_macro	0.5235309829059829
gptr_nt_q4d4_mt	all	citation_support_micro	0.8253012048192772
gptr_nt_q4d4_mt	all	citation_support_macro	0.8206026612276612
gptr_nt_q4d4_mt	all	sentence_support_micro	0.8242424242424242
gptr_nt_q4d4_mt	all	sentence_support_macro	0.8195609945609945
gptr_nt_q4d4_mt	all	nugget_coverage_micro	0.27116564417177913
gptr_nt_q4d4_mt	all	nugget_coverage_macro	0.35362469691970927
gptr_nt_q4d4_mt	all	nugget_coverage_weighted_micro	0.3228511530398323
gptr_nt_q4d4_mt	all	nugget_coverage_weighted_macro	0.378361178703573
gptr_nt_q4d4_mt	all	f1_micro	0.40807847663012115
gptr_nt_q4d4_mt	all	f1_macro	0.466048490382222
gptr_nt_q4d4_mt	all	f1_weighted_micro	0.4639684543984404
gptr_nt_q4d4_mt	all	f1_weighted_macro	0.47420755777690127
gptr_nt_q4d4_mt	1001	sentences	10.0
gptr_nt_q4d4_mt	1001	character_count	1541.0
gptr_nt_q4d4_mt	1001	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1001	correctly_cited_sentences	9.0
gptr_nt_q4d4_mt	1001	nuggets	101.0
gptr_nt_q4d4_mt	1001	nuggets_weighted	110.0
gptr_nt_q4d4_mt	1001	correct_nuggets	40.0
gptr_nt_q4d4_mt	1001	correct_nuggets_weighted	46.0
gptr_nt_q4d4_mt	1001	citations	10.0
gptr_nt_q4d4_mt	1001	relevant_citations	4.0
gptr_nt_q4d4_mt	1001	supporting_citations	9.0
gptr_nt_q4d4_mt	1001	citation_relevance	0.4
gptr_nt_q4d4_mt	1001	citation_support	0.9
gptr_nt_q4d4_mt	1001	sentence_support	0.9
gptr_nt_q4d4_mt	1001	nugget_coverage	0.39603960396039606
gptr_nt_q4d4_mt	1001	nugget_coverage_weighted	0.41818181818181815
gptr_nt_q4d4_mt	1001	f1	0.5500381970970206
gptr_nt_q4d4_mt	1001	f1_weighted	0.5710344827586207
gptr_nt_q4d4_mt	1003	sentences	10.0
gptr_nt_q4d4_mt	1003	character_count	1808.0
gptr_nt_q4d4_mt	1003	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1003	correctly_cited_sentences	8.0
gptr_nt_q4d4_mt	1003	nuggets	103.0
gptr_nt_q4d4_mt	1003	nuggets_weighted	26.0
gptr_nt_q4d4_mt	1003	correct_nuggets	18.0
gptr_nt_q4d4_mt	1003	correct_nuggets_weighted	4.0
gptr_nt_q4d4_mt	1003	citations	10.0
gptr_nt_q4d4_mt	1003	relevant_citations	5.0
gptr_nt_q4d4_mt	1003	supporting_citations	8.0
gptr_nt_q4d4_mt	1003	citation_relevance	0.5
gptr_nt_q4d4_mt	1003	citation_support	0.8
gptr_nt_q4d4_mt	1003	sentence_support	0.8
gptr_nt_q4d4_mt	1003	nugget_coverage	0.17475728155339806
gptr_nt_q4d4_mt	1003	nugget_coverage_weighted	0.15384615384615385
gptr_nt_q4d4_mt	1003	f1	0.28685258964143423
gptr_nt_q4d4_mt	1003	f1_weighted	0.25806451612903225
gptr_nt_q4d4_mt	1005	sentences	10.0
gptr_nt_q4d4_mt	1005	character_count	1828.0
gptr_nt_q4d4_mt	1005	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1005	correctly_cited_sentences	9.0
gptr_nt_q4d4_mt	1005	nuggets	111.0
gptr_nt_q4d4_mt	1005	nuggets_weighted	32.0
gptr_nt_q4d4_mt	1005	correct_nuggets	21.0
gptr_nt_q4d4_mt	1005	correct_nuggets_weighted	4.0
gptr_nt_q4d4_mt	1005	citations	10.0
gptr_nt_q4d4_mt	1005	relevant_citations	4.0
gptr_nt_q4d4_mt	1005	supporting_citations	9.0
gptr_nt_q4d4_mt	1005	citation_relevance	0.4
gptr_nt_q4d4_mt	1005	citation_support	0.9
gptr_nt_q4d4_mt	1005	sentence_support	0.9
gptr_nt_q4d4_mt	1005	nugget_coverage	0.1891891891891892
gptr_nt_q4d4_mt	1005	nugget_coverage_weighted	0.125
gptr_nt_q4d4_mt	1005	f1	0.31265508684863524
gptr_nt_q4d4_mt	1005	f1_weighted	0.21951219512195125
gptr_nt_q4d4_mt	1007	sentences	10.0
gptr_nt_q4d4_mt	1007	character_count	1492.0
gptr_nt_q4d4_mt	1007	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1007	correctly_cited_sentences	8.0
gptr_nt_q4d4_mt	1007	nuggets	22.0
gptr_nt_q4d4_mt	1007	nuggets_weighted	6.0
gptr_nt_q4d4_mt	1007	correct_nuggets	11.0
gptr_nt_q4d4_mt	1007	correct_nuggets_weighted	2.0
gptr_nt_q4d4_mt	1007	citations	10.0
gptr_nt_q4d4_mt	1007	relevant_citations	10.0
gptr_nt_q4d4_mt	1007	supporting_citations	8.0
gptr_nt_q4d4_mt	1007	citation_relevance	1.0
gptr_nt_q4d4_mt	1007	citation_support	0.8
gptr_nt_q4d4_mt	1007	sentence_support	0.8
gptr_nt_q4d4_mt	1007	nugget_coverage	0.5
gptr_nt_q4d4_mt	1007	nugget_coverage_weighted	0.3333333333333333
gptr_nt_q4d4_mt	1007	f1	0.6153846153846154
gptr_nt_q4d4_mt	1007	f1_weighted	0.47058823529411764
gptr_nt_q4d4_mt	1009	sentences	12.0
gptr_nt_q4d4_mt	1009	character_count	1403.0
gptr_nt_q4d4_mt	1009	sentences_with_citations_or_requiring_citations	11.0
gptr_nt_q4d4_mt	1009	correctly_cited_sentences	10.0
gptr_nt_q4d4_mt	1009	nuggets	15.0
gptr_nt_q4d4_mt	1009	nuggets_weighted	8.0
gptr_nt_q4d4_mt	1009	correct_nuggets	9.0
gptr_nt_q4d4_mt	1009	correct_nuggets_weighted	6.0
gptr_nt_q4d4_mt	1009	citations	12.0
gptr_nt_q4d4_mt	1009	relevant_citations	11.0
gptr_nt_q4d4_mt	1009	supporting_citations	11.0
gptr_nt_q4d4_mt	1009	citation_relevance	0.9166666666666666
gptr_nt_q4d4_mt	1009	citation_support	0.9166666666666666
gptr_nt_q4d4_mt	1009	sentence_support	0.9090909090909091
gptr_nt_q4d4_mt	1009	nugget_coverage	0.6
gptr_nt_q4d4_mt	1009	nugget_coverage_weighted	0.75
gptr_nt_q4d4_mt	1009	f1	0.7228915662650602
gptr_nt_q4d4_mt	1009	f1_weighted	0.821917808219178
gptr_nt_q4d4_mt	1011	sentences	11.0
gptr_nt_q4d4_mt	1011	character_count	1268.0
gptr_nt_q4d4_mt	1011	sentences_with_citations_or_requiring_citations	11.0
gptr_nt_q4d4_mt	1011	correctly_cited_sentences	10.0
gptr_nt_q4d4_mt	1011	nuggets	63.0
gptr_nt_q4d4_mt	1011	nuggets_weighted	40.0
gptr_nt_q4d4_mt	1011	correct_nuggets	20.0
gptr_nt_q4d4_mt	1011	correct_nuggets_weighted	14.0
gptr_nt_q4d4_mt	1011	citations	11.0
gptr_nt_q4d4_mt	1011	relevant_citations	0.0
gptr_nt_q4d4_mt	1011	supporting_citations	10.0
gptr_nt_q4d4_mt	1011	citation_relevance	0.0
gptr_nt_q4d4_mt	1011	citation_support	0.9090909090909091
gptr_nt_q4d4_mt	1011	sentence_support	0.9090909090909091
gptr_nt_q4d4_mt	1011	nugget_coverage	0.31746031746031744
gptr_nt_q4d4_mt	1011	nugget_coverage_weighted	0.35
gptr_nt_q4d4_mt	1011	f1	0.4705882352941177
gptr_nt_q4d4_mt	1011	f1_weighted	0.5054151624548736
gptr_nt_q4d4_mt	1013	sentences	13.0
gptr_nt_q4d4_mt	1013	character_count	1427.0
gptr_nt_q4d4_mt	1013	sentences_with_citations_or_requiring_citations	13.0
gptr_nt_q4d4_mt	1013	correctly_cited_sentences	12.0
gptr_nt_q4d4_mt	1013	nuggets	26.0
gptr_nt_q4d4_mt	1013	nuggets_weighted	12.0
gptr_nt_q4d4_mt	1013	correct_nuggets	15.0
gptr_nt_q4d4_mt	1013	correct_nuggets_weighted	12.0
gptr_nt_q4d4_mt	1013	citations	13.0
gptr_nt_q4d4_mt	1013	relevant_citations	8.0
gptr_nt_q4d4_mt	1013	supporting_citations	12.0
gptr_nt_q4d4_mt	1013	citation_relevance	0.6153846153846154
gptr_nt_q4d4_mt	1013	citation_support	0.9230769230769231
gptr_nt_q4d4_mt	1013	sentence_support	0.9230769230769231
gptr_nt_q4d4_mt	1013	nugget_coverage	0.5769230769230769
gptr_nt_q4d4_mt	1013	nugget_coverage_weighted	1.0
gptr_nt_q4d4_mt	1013	f1	0.7100591715976331
gptr_nt_q4d4_mt	1013	f1_weighted	0.9600000000000001
gptr_nt_q4d4_mt	1017	sentences	9.0
gptr_nt_q4d4_mt	1017	character_count	1665.0
gptr_nt_q4d4_mt	1017	sentences_with_citations_or_requiring_citations	9.0
gptr_nt_q4d4_mt	1017	correctly_cited_sentences	8.0
gptr_nt_q4d4_mt	1017	nuggets	109.0
gptr_nt_q4d4_mt	1017	nuggets_weighted	62.0
gptr_nt_q4d4_mt	1017	correct_nuggets	22.0
gptr_nt_q4d4_mt	1017	correct_nuggets_weighted	16.0
gptr_nt_q4d4_mt	1017	citations	9.0
gptr_nt_q4d4_mt	1017	relevant_citations	4.0
gptr_nt_q4d4_mt	1017	supporting_citations	8.0
gptr_nt_q4d4_mt	1017	citation_relevance	0.4444444444444444
gptr_nt_q4d4_mt	1017	citation_support	0.8888888888888888
gptr_nt_q4d4_mt	1017	sentence_support	0.8888888888888888
gptr_nt_q4d4_mt	1017	nugget_coverage	0.2018348623853211
gptr_nt_q4d4_mt	1017	nugget_coverage_weighted	0.25806451612903225
gptr_nt_q4d4_mt	1017	f1	0.32897196261682243
gptr_nt_q4d4_mt	1017	f1_weighted	0.39999999999999997
gptr_nt_q4d4_mt	1025	sentences	10.0
gptr_nt_q4d4_mt	1025	character_count	1820.0
gptr_nt_q4d4_mt	1025	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1025	correctly_cited_sentences	8.0
gptr_nt_q4d4_mt	1025	nuggets	12.0
gptr_nt_q4d4_mt	1025	nuggets_weighted	20.0
gptr_nt_q4d4_mt	1025	correct_nuggets	9.0
gptr_nt_q4d4_mt	1025	correct_nuggets_weighted	14.0
gptr_nt_q4d4_mt	1025	citations	11.0
gptr_nt_q4d4_mt	1025	relevant_citations	4.0
gptr_nt_q4d4_mt	1025	supporting_citations	8.0
gptr_nt_q4d4_mt	1025	citation_relevance	0.36363636363636365
gptr_nt_q4d4_mt	1025	citation_support	0.7272727272727273
gptr_nt_q4d4_mt	1025	sentence_support	0.8
gptr_nt_q4d4_mt	1025	nugget_coverage	0.75
gptr_nt_q4d4_mt	1025	nugget_coverage_weighted	0.7
gptr_nt_q4d4_mt	1025	f1	0.7741935483870969
gptr_nt_q4d4_mt	1025	f1_weighted	0.7466666666666666
gptr_nt_q4d4_mt	1027	sentences	10.0
gptr_nt_q4d4_mt	1027	character_count	1698.0
gptr_nt_q4d4_mt	1027	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1027	correctly_cited_sentences	10.0
gptr_nt_q4d4_mt	1027	nuggets	7.0
gptr_nt_q4d4_mt	1027	nuggets_weighted	10.0
gptr_nt_q4d4_mt	1027	correct_nuggets	4.0
gptr_nt_q4d4_mt	1027	correct_nuggets_weighted	6.0
gptr_nt_q4d4_mt	1027	citations	10.0
gptr_nt_q4d4_mt	1027	relevant_citations	4.0
gptr_nt_q4d4_mt	1027	supporting_citations	10.0
gptr_nt_q4d4_mt	1027	citation_relevance	0.4
gptr_nt_q4d4_mt	1027	citation_support	1.0
gptr_nt_q4d4_mt	1027	sentence_support	1.0
gptr_nt_q4d4_mt	1027	nugget_coverage	0.5714285714285714
gptr_nt_q4d4_mt	1027	nugget_coverage_weighted	0.6
gptr_nt_q4d4_mt	1027	f1	0.7272727272727273
gptr_nt_q4d4_mt	1027	f1_weighted	0.7499999999999999
gptr_nt_q4d4_mt	1029	sentences	10.0
gptr_nt_q4d4_mt	1029	character_count	1674.0
gptr_nt_q4d4_mt	1029	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1029	correctly_cited_sentences	8.0
gptr_nt_q4d4_mt	1029	nuggets	106.0
gptr_nt_q4d4_mt	1029	nuggets_weighted	58.0
gptr_nt_q4d4_mt	1029	correct_nuggets	15.0
gptr_nt_q4d4_mt	1029	correct_nuggets_weighted	6.0
gptr_nt_q4d4_mt	1029	citations	10.0
gptr_nt_q4d4_mt	1029	relevant_citations	7.0
gptr_nt_q4d4_mt	1029	supporting_citations	8.0
gptr_nt_q4d4_mt	1029	citation_relevance	0.7
gptr_nt_q4d4_mt	1029	citation_support	0.8
gptr_nt_q4d4_mt	1029	sentence_support	0.8
gptr_nt_q4d4_mt	1029	nugget_coverage	0.14150943396226415
gptr_nt_q4d4_mt	1029	nugget_coverage_weighted	0.10344827586206896
gptr_nt_q4d4_mt	1029	f1	0.24048096192384769
gptr_nt_q4d4_mt	1029	f1_weighted	0.183206106870229
gptr_nt_q4d4_mt	1033	sentences	12.0
gptr_nt_q4d4_mt	1033	character_count	1881.0
gptr_nt_q4d4_mt	1033	sentences_with_citations_or_requiring_citations	11.0
gptr_nt_q4d4_mt	1033	correctly_cited_sentences	10.0
gptr_nt_q4d4_mt	1033	nuggets	56.0
gptr_nt_q4d4_mt	1033	nuggets_weighted	28.0
gptr_nt_q4d4_mt	1033	correct_nuggets	15.0
gptr_nt_q4d4_mt	1033	correct_nuggets_weighted	10.0
gptr_nt_q4d4_mt	1033	citations	11.0
gptr_nt_q4d4_mt	1033	relevant_citations	7.0
gptr_nt_q4d4_mt	1033	supporting_citations	10.0
gptr_nt_q4d4_mt	1033	citation_relevance	0.6363636363636364
gptr_nt_q4d4_mt	1033	citation_support	0.9090909090909091
gptr_nt_q4d4_mt	1033	sentence_support	0.9090909090909091
gptr_nt_q4d4_mt	1033	nugget_coverage	0.26785714285714285
gptr_nt_q4d4_mt	1033	nugget_coverage_weighted	0.35714285714285715
gptr_nt_q4d4_mt	1033	f1	0.41379310344827586
gptr_nt_q4d4_mt	1033	f1_weighted	0.5128205128205129
gptr_nt_q4d4_mt	1041	sentences	11.0
gptr_nt_q4d4_mt	1041	character_count	1795.0
gptr_nt_q4d4_mt	1041	sentences_with_citations_or_requiring_citations	11.0
gptr_nt_q4d4_mt	1041	correctly_cited_sentences	9.0
gptr_nt_q4d4_mt	1041	first_instance_sentences_missing_citation	1.0
gptr_nt_q4d4_mt	1041	nuggets	22.0
gptr_nt_q4d4_mt	1041	nuggets_weighted	10.0
gptr_nt_q4d4_mt	1041	correct_nuggets	9.0
gptr_nt_q4d4_mt	1041	correct_nuggets_weighted	2.0
gptr_nt_q4d4_mt	1041	citations	10.0
gptr_nt_q4d4_mt	1041	relevant_citations	4.0
gptr_nt_q4d4_mt	1041	supporting_citations	9.0
gptr_nt_q4d4_mt	1041	citation_relevance	0.4
gptr_nt_q4d4_mt	1041	citation_support	0.9
gptr_nt_q4d4_mt	1041	sentence_support	0.8181818181818182
gptr_nt_q4d4_mt	1041	nugget_coverage	0.4090909090909091
gptr_nt_q4d4_mt	1041	nugget_coverage_weighted	0.2
gptr_nt_q4d4_mt	1041	f1	0.5454545454545455
gptr_nt_q4d4_mt	1041	f1_weighted	0.32142857142857145
gptr_nt_q4d4_mt	1053	sentences	10.0
gptr_nt_q4d4_mt	1053	character_count	1432.0
gptr_nt_q4d4_mt	1053	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1053	correctly_cited_sentences	8.0
gptr_nt_q4d4_mt	1053	nuggets	21.0
gptr_nt_q4d4_mt	1053	nuggets_weighted	14.0
gptr_nt_q4d4_mt	1053	correct_nuggets	9.0
gptr_nt_q4d4_mt	1053	correct_nuggets_weighted	8.0
gptr_nt_q4d4_mt	1053	citations	10.0
gptr_nt_q4d4_mt	1053	relevant_citations	8.0
gptr_nt_q4d4_mt	1053	supporting_citations	8.0
gptr_nt_q4d4_mt	1053	citation_relevance	0.8
gptr_nt_q4d4_mt	1053	citation_support	0.8
gptr_nt_q4d4_mt	1053	sentence_support	0.8
gptr_nt_q4d4_mt	1053	nugget_coverage	0.42857142857142855
gptr_nt_q4d4_mt	1053	nugget_coverage_weighted	0.5714285714285714
gptr_nt_q4d4_mt	1053	f1	0.5581395348837209
gptr_nt_q4d4_mt	1053	f1_weighted	0.6666666666666666
gptr_nt_q4d4_mt	1065	sentences	10.0
gptr_nt_q4d4_mt	1065	character_count	1727.0
gptr_nt_q4d4_mt	1065	sentences_with_citations_or_requiring_citations	10.0
gptr_nt_q4d4_mt	1065	correctly_cited_sentences	4.0
gptr_nt_q4d4_mt	1065	nuggets	30.0
gptr_nt_q4d4_mt	1065	nuggets_weighted	30.0
gptr_nt_q4d4_mt	1065	correct_nuggets	4.0
gptr_nt_q4d4_mt	1065	correct_nuggets_weighted	4.0
gptr_nt_q4d4_mt	1065	citations	10.0
gptr_nt_q4d4_mt	1065	relevant_citations	8.0
gptr_nt_q4d4_mt	1065	supporting_citations	4.0
gptr_nt_q4d4_mt	1065	citation_relevance	0.8
gptr_nt_q4d4_mt	1065	citation_support	0.4
gptr_nt_q4d4_mt	1065	sentence_support	0.4
gptr_nt_q4d4_mt	1065	nugget_coverage	0.13333333333333333
gptr_nt_q4d4_mt	1065	nugget_coverage_weighted	0.13333333333333333
gptr_nt_q4d4_mt	1065	f1	0.2
gptr_nt_q4d4_mt	1065	f1_weighted	0.2
gptr_nt_q4d4_mt	1069	sentences	9.0
gptr_nt_q4d4_mt	1069	character_count	1155.0
gptr_nt_q4d4_mt	1069	sentences_with_citations_or_requiring_citations	9.0
gptr_nt_q4d4_mt	1069	correctly_cited_sentences	5.0
gptr_nt_q4d4_mt	1069	nuggets	11.0
gptr_nt_q4d4_mt	1069	nuggets_weighted	11.0
gptr_nt_q4d4_mt	1069	correct_nuggets	0.0
gptr_nt_q4d4_mt	1069	correct_nuggets_weighted	0.0
gptr_nt_q4d4_mt	1069	citations	9.0
gptr_nt_q4d4_mt	1069	relevant_citations	0.0
gptr_nt_q4d4_mt	1069	supporting_citations	5.0
gptr_nt_q4d4_mt	1069	citation_relevance	0.0
gptr_nt_q4d4_mt	1069	citation_support	0.5555555555555556
gptr_nt_q4d4_mt	1069	sentence_support	0.5555555555555556
gptr_nt_q4d4_mt	1069	nugget_coverage	0.0
gptr_nt_q4d4_mt	1069	nugget_coverage_weighted	0.0
gptr_nt_q4d4_mt	1069	f1	0.0
gptr_nt_q4d4_mt	1069	f1_weighted	0.0