dp-zp-agent/experiments/graphrag/results/answers_v6_dev_2026-10-25/answers_dev.csv

2.7 KiB

1idcategorystricterrorlatency_secondsattemptsfirst_pass_strict
2wide-001shared_keyword_pairTrue14.980318888992771True
3wide-002shared_keyword_pairTrue8.3973932440130741True
4wide-041same_academic_year_pairTrue6.9026438290020451True
5wide-042same_academic_year_pairTrue6.8823754920013021True
6wide-080same_academic_year_pairTrue12.2717576860013651True
7wide-081same_start_year_pairTrue8.2047274900105551True
8wide-082same_start_year_pairTrue13.7026115519984161True
9wide-104same_start_year_pairTrue6.5018202759965791True
10wide-113person_title_yearTrue10.9647963150055151True
11wide-114person_title_yearTrue7.3766250979970211True
12wide-116person_title_yearTrue7.8471947620128051True
13wide-119person_title_yearTrue7.3429802699974971True
14wide-129person_title_yearTrue8.4188761460100071True
15wide-137person_keyword_titleTrue9.7951947699912131True
16wide-138person_keyword_titleTrue8.8445609710033751True
17wide-139person_keyword_titleTrue9.3293345529964431True
18wide-141person_keyword_titleTrue9.5928777500084831True
19wide-142person_keyword_titleTrue5.0078028110001471True
20wide-143person_keyword_titleTrue11.6640195240033791True
21wide-145person_keyword_titleTrue3.29149135400075471True
22wide-155person_keyword_titleTrue6.6808257020020391True
23wide-159person_keyword_titleTrue13.5608245610055751True
24wide-161person_keyword_titleTrue7.2875503429968381True
25wide-163person_keyword_titleTrue12.331438881999931True
26wide-165person_keyword_titleTrue2.51200010800675951True
27wide-169document_author_category_multi_hopTrue6.51305449299979951True
28wide-170document_author_category_multi_hopTrue8.981619775993751True
29wide-178document_author_category_multi_hopTrue6.0776338900031991True
30wide-181document_author_category_multi_hopTrue8.4411539980064841True
31wide-193person_multiple_categoriesTrue5.5235570330114571True
32wide-194person_multiple_categoriesTrue8.16420890900191True
33wide-209person_multiple_categoriesTrue6.14623353199567651True
34wide-217candidate_set_aggregationTrue10.3332945099973591True
35wide-218candidate_set_aggregationTrue8.6588899189955551True
36wide-232candidate_set_aggregationTrue14.3361499340098821True
37wide-236candidate_set_aggregationTrue7.8961739509977631True
38wide-239candidate_set_aggregationTrue13.9609325839992381True
39wide-249conjunctive_disambiguationTrue5.2885972829972161True
40wide-250conjunctive_disambiguationTrue10.1460737700108441True
41wide-283conjunctive_disambiguationFalse12.3963724329951221False
42wide-289negative_lookupTrue6.8128682370006571True
43wide-290negative_lookupTrue6.79160783800762151True