dp-zp-agent/experiments/graphrag/results/answers_v6_regression_2026-10-25/answers_regression.csv

20 KiB

1idcategorystricterrorlatency_secondsattemptsfirst_pass_strict
2wide-001shared_keyword_pairTrue46.6732225789892251True
3wide-002shared_keyword_pairTrue8.5599338369938781True
4wide-003shared_keyword_pairTrue7.5993642899993571True
5wide-004shared_keyword_pairTrue43.054316271009161True
6wide-005shared_keyword_pairTrue46.602775324994581True
7wide-006shared_keyword_pairTrue17.021981961996061True
8wide-007shared_keyword_pairTrue37.584516747010641True
9wide-008shared_keyword_pairTrue162.563057706007381True
10wide-009shared_keyword_pairTrue96.590993883000921True
11wide-010shared_keyword_pairTrue98.126942046990731True
12wide-011shared_keyword_pairTrue5.0237043710076251True
13wide-012shared_keyword_pairTrue4.5116612800047731True
14wide-013shared_keyword_pairTrue4.72686356700432951True
15wide-014shared_keyword_pairTrue4.4116141740087191True
16wide-015shared_keyword_pairTrue7.3576048459945011True
17wide-016shared_keyword_pairTrue8.7663504230004041True
18wide-017shared_keyword_pairTrue7.0751481120096291True
19wide-018shared_keyword_pairTrue7.2739964279899141True
20wide-019shared_keyword_pairTrue7.3055659109959381True
21wide-020shared_keyword_pairTrue6.6278477820014811True
22wide-021shared_keyword_pairTrue8.0899558570090451True
23wide-022shared_keyword_pairTrue7.4790663040039361True
24wide-023shared_keyword_pairTrue12.7678350269998191True
25wide-024shared_keyword_pairTrue12.188261782997871True
26wide-025shared_keyword_pairTrue24.2961054839979621True
27wide-026shared_keyword_pairTrue26.2568274910008771True
28wide-027shared_keyword_pairTrue21.5119694520108171True
29wide-028shared_keyword_pairTrue13.6901017890049841True
30wide-029shared_keyword_pairTrue8.3944146480062051True
31wide-030shared_keyword_pairTrue13.5387308539939111True
32wide-031shared_keyword_pairTrue8.4473070580133941True
33wide-032shared_keyword_pairTrue13.3138539040082831True
34wide-033shared_keyword_pairTrue8.7483171889907681True
35wide-034shared_keyword_pairTrue15.0757564939995061True
36wide-035shared_keyword_pairTrue7.74716482800431551True
37wide-036shared_keyword_pairTrue12.8419847469922391True
38wide-037shared_keyword_pairTrue8.5775438389973711True
39wide-038shared_keyword_pairTrue12.7188463659986161True
40wide-039shared_keyword_pairTrue9.088337159992081True
41wide-040shared_keyword_pairTrue13.9801100790064081True
42wide-041same_academic_year_pairTrue7.1456614539929431True
43wide-042same_academic_year_pairTrue11.6845782479940681True
44wide-043same_academic_year_pairTrue10.0499505539919481True
45wide-044same_academic_year_pairTrue12.462435859997641True
46wide-045same_academic_year_pairTrue9.9496396840113451True
47wide-046same_academic_year_pairTrue10.849675789999311True
48wide-047same_academic_year_pairTrue11.9290213249914811True
49wide-048same_academic_year_pairTrue12.542776285001311True
50wide-049same_academic_year_pairTrue12.5129205779958281True
51wide-050same_academic_year_pairTrue10.9437232050113381True
52wide-051same_academic_year_pairTrue11.3610789719969031True
53wide-052same_academic_year_pairTrue10.1270269309898141True
54wide-053same_academic_year_pairTrue9.6710260559921151True
55wide-054same_academic_year_pairTrue10.909428022001521True
56wide-055same_academic_year_pairTrue9.6501525009953181True
57wide-056same_academic_year_pairTrue13.776390847007861True
58wide-057same_academic_year_pairTrue7.5197700800054011True
59wide-058same_academic_year_pairTrue12.2267944890045331True
60wide-059same_academic_year_pairTrue9.185162552996191True
61wide-060same_academic_year_pairTrue11.2676763240015131True
62wide-061same_academic_year_pairTrue8.9712329450121621True
63wide-062same_academic_year_pairTrue10.0022403230104831True
64wide-063same_academic_year_pairTrue9.589870165000321True
65wide-064same_academic_year_pairTrue9.8890495319938051True
66wide-065same_academic_year_pairTrue10.52991817300791True
67wide-066same_academic_year_pairTrue9.4142928490036871True
68wide-067same_academic_year_pairTrue12.7952676300046731True
69wide-068same_academic_year_pairTrue7.4657572750002151True
70wide-069same_academic_year_pairTrue13.188607083997341True
71wide-070same_academic_year_pairTrue6.8706176800042161True
72wide-071same_academic_year_pairTrue13.9284969299915251True
73wide-072same_academic_year_pairTrue6.4187713390128921True
74wide-073same_academic_year_pairTrue11.9173433200048751True
75wide-074same_academic_year_pairTrue8.2774253959942141True
76wide-075same_academic_year_pairTrue10.8301950900058731True
77wide-076same_academic_year_pairTrue8.490582254002221True
78wide-077same_academic_year_pairTrue10.7181312810134841True
79wide-078same_academic_year_pairTrue8.9511867340042951True
80wide-079same_academic_year_pairTrue10.6181726789945971True
81wide-080same_academic_year_pairTrue9.4632164759968871True
82wide-081same_start_year_pairTrue10.8347322460031141True
83wide-082same_start_year_pairTrue9.7317017439927441True
84wide-083same_start_year_pairTrue10.4924858940066771True
85wide-084same_start_year_pairTrue9.8001669649966061True
86wide-085same_start_year_pairTrue10.2721055730071381True
87wide-086same_start_year_pairTrue9.519159324001521True
88wide-087same_start_year_pairTrue9.9216995270107871True
89wide-088same_start_year_pairTrue9.5246954140020531True
90wide-089same_start_year_pairTrue10.7974897149979371True
91wide-090same_start_year_pairTrue9.7933656209934271True
92wide-091same_start_year_pairTrue10.9775259089947211True
93wide-092same_start_year_pairTrue8.9569338870060161True
94wide-093same_start_year_pairTrue10.823727337003221True
95wide-094same_start_year_pairTrue8.4924659750104181True
96wide-095same_start_year_pairTrue11.660259547003081True
97wide-096same_start_year_pairTrue8.6069514180126131True
98wide-097same_start_year_pairTrue12.1649146419949831True
99wide-098same_start_year_pairTrue8.517341551007121True
100wide-099same_start_year_pairTrue12.0079757229977991True
101wide-100same_start_year_pairTrue8.0855747630121191True
102wide-101same_start_year_pairTrue11.3813935740035961True
103wide-102same_start_year_pairTrue8.1054800849960881True
104wide-103same_start_year_pairTrue11.1784951220033691True
105wide-104same_start_year_pairFalse8.0459266260004371False
106wide-105same_start_year_pairTrue11.052173442003551True
107wide-106same_start_year_pairTrue8.1586183100007471True
108wide-107same_start_year_pairTrue10.9081504049972861True
109wide-108same_start_year_pairTrue8.8804179159924391True
110wide-109same_start_year_pairTrue11.1872530980035661True
111wide-110same_start_year_pairTrue9.3948315769957841True
112wide-111same_start_year_pairTrue10.5239624630048641True
113wide-112same_start_year_pairTrue8.8989464850019431True
114wide-113person_title_yearTrue9.4186832770064941True
115wide-114person_title_yearTrue8.1677813790010991True
116wide-115person_title_yearTrue8.7136971270083451True
117wide-116person_title_yearTrue7.51550749300804451True
118wide-117person_title_yearTrue8.7926612720038971True
119wide-118person_title_yearTrue7.7290411510039121True
120wide-119person_title_yearFalseInvalidAnswerFormat: two invalid JSON/schema responses17.0426948870008352False
121wide-120person_title_yearTrue7.2938940770109181True
122wide-121person_title_yearTrue9.9122950320015661True
123wide-122person_title_yearTrue10.3365266059990971True
124wide-123person_title_yearTrue7.5572569499927341True
125wide-124person_title_yearTrue9.9723756399907871True
126wide-125person_title_yearTrue6.45792894999613051True
127wide-126person_title_yearTrue8.7069658819964391True
128wide-127person_title_yearTrue6.5283630829944741True
129wide-128person_title_yearTrue9.742504774010741True
130wide-129person_title_yearTrue7.8167604659975041True
131wide-130person_title_yearTrue9.0371854949917181True
132wide-131person_title_yearTrue6.9806357869965721True
133wide-132person_title_yearTrue8.1332844940043291True
134wide-133person_title_yearTrue7.6970973849965961True
135wide-134person_title_yearTrue7.9803298679908041True
136wide-135person_title_yearTrue7.8901919810014081True
137wide-136person_title_yearTrue8.5215504039952071True
138wide-137person_keyword_titleTrue8.6540033899946141True
139wide-138person_keyword_titleTrue9.3179250559915091True
140wide-139person_keyword_titleTrue8.4432551080099071True
141wide-140person_keyword_titleTrue9.2683550770016151True
142wide-141person_keyword_titleTrue8.6195616079930911True
143wide-142person_keyword_titleTrue4.8428238010092171True
144wide-143person_keyword_titleFalseInvalidAnswerFormat: two invalid JSON/schema responses25.418261439001072False
145wide-144person_keyword_titleTrue6.5200406780058981True
146wide-145person_keyword_titleTrue6.4823678810062121True
147wide-146person_keyword_titleTrue7.9269334770069691True
148wide-147person_keyword_titleTrue9.2586052990081951True
149wide-148person_keyword_titleTrue7.4773493380052971True
150wide-149person_keyword_titleTrue11.0219100499962221True
151wide-150person_keyword_titleTrue9.1066263569955481True
152wide-151person_keyword_titleTrue9.879952942996171True
153wide-152person_keyword_titleTrue8.4000235059938861True
154wide-153person_keyword_titleTrue8.5749255720002111True
155wide-154person_keyword_titleTrue8.5800533540023031True
156wide-155person_keyword_titleTrue9.0838584010052731True
157wide-156person_keyword_titleTrue8.6191254209988981True
158wide-157person_keyword_titleTrue9.0713853199995361True
159wide-158person_keyword_titleTrue8.343096801996581True
160wide-159person_keyword_titleTrue9.8220200930081771True
161wide-160person_keyword_titleTrue9.1662243979953931True
162wide-161person_keyword_titleTrue10.3587298459897281True
163wide-162person_keyword_titleTrue8.4442430130002321True
164wide-163person_keyword_titleTrue9.7134107059973761True
165wide-164person_keyword_titleTrue8.844759686995531True
166wide-165person_keyword_titleTrue5.3328550199948951True
167wide-166person_keyword_titleTrue7.2850087480037471True
168wide-167person_keyword_titleTrue7.7217757199978221True
169wide-168person_keyword_titleTrue10.3341258889995521True
170wide-169document_author_category_multi_hopTrue5.70365903701167551True
171wide-170document_author_category_multi_hopTrue9.7545296600001171True
172wide-171document_author_category_multi_hopTrue4.67462413299654141True
173wide-172document_author_category_multi_hopTrue9.6199214799999031True
174wide-173document_author_category_multi_hopTrue6.2149227990012151True
175wide-174document_author_category_multi_hopTrue8.835087237996051True
176wide-175document_author_category_multi_hopTrue6.0346102150069781True
177wide-176document_author_category_multi_hopFalseInvalidAnswerFormat: two invalid JSON/schema responses30.1486103640054352False
178wide-177document_author_category_multi_hopTrue5.493712925992441True
179wide-178document_author_category_multi_hopTrue8.3428994419955421True
180wide-179document_author_category_multi_hopTrue9.6400736130017321True
181wide-180document_author_category_multi_hopTrue7.4657609630085061True
182wide-181document_author_category_multi_hopTrue5.7945084020029751True
183wide-182document_author_category_multi_hopTrue8.318497200001731True
184wide-183document_author_category_multi_hopTrue9.8572322660038481True
185wide-184document_author_category_multi_hopTrue6.4445209879922911True
186wide-185document_author_category_multi_hopTrue9.5220224410004451True
187wide-186document_author_category_multi_hopTrue6.4134966490091761True
188wide-187document_author_category_multi_hopTrue10.4106270940101241True
189wide-188document_author_category_multi_hopTrue5.2311396519944541True
190wide-189document_author_category_multi_hopTrue8.7948491900024241True
191wide-190document_author_category_multi_hopTrue4.9444737629964951True
192wide-191document_author_category_multi_hopTrue10.0421163179998981True
193wide-192document_author_category_multi_hopTrue10.54072179000651True
194wide-193person_multiple_categoriesTrue4.7925280199997361True
195wide-194person_multiple_categoriesTrue4.7829161900008331True
196wide-195person_multiple_categoriesTrue8.6154756549949521True
197wide-196person_multiple_categoriesTrue4.3236369310034211True
198wide-197person_multiple_categoriesTrue7.4031067199975951True
199wide-198person_multiple_categoriesTrue5.5805198540037961True
200wide-199person_multiple_categoriesTrue7.4287121749948711True
201wide-200person_multiple_categoriesTrue5.6285097699874311True
202wide-201person_multiple_categoriesTrue7.04068750399164861True
203wide-202person_multiple_categoriesTrue5.4286485259945041True
204wide-203person_multiple_categoriesTrue7.36718337199999951True
205wide-204person_multiple_categoriesTrue6.0627374860050621True
206wide-205person_multiple_categoriesTrue7.7034951450041261True
207wide-206person_multiple_categoriesTrue6.0371945660008351True
208wide-207person_multiple_categoriesTrue6.86269326601177451True
209wide-208person_multiple_categoriesTrue5.6147485370020151True
210wide-209person_multiple_categoriesTrue7.4103571879968511True
211wide-210person_multiple_categoriesTrue5.7737883810041241True
212wide-211person_multiple_categoriesTrue8.4623417530092411True
213wide-212person_multiple_categoriesTrue3.93565383499662861True
214wide-213person_multiple_categoriesTrue7.34886706799443351True
215wide-214person_multiple_categoriesTrue5.4403275139920881True
216wide-215person_multiple_categoriesTrue7.4793257370038191True
217wide-216person_multiple_categoriesTrue5.4889110340009211True
218wide-217candidate_set_aggregationTrue12.3229151139967141True
219wide-218candidate_set_aggregationTrue7.9396874450030741True
220wide-219candidate_set_aggregationTrue15.701257292996161True
221wide-220candidate_set_aggregationTrue7.4905746160075071True
222wide-221candidate_set_aggregationTrue14.2665503140015061True
223wide-222candidate_set_aggregationTrue9.2853328480123311True
224wide-223candidate_set_aggregationTrue15.1661980470089471True
225wide-224candidate_set_aggregationTrue7.2999343190022051True
226wide-225candidate_set_aggregationTrue12.342214894000791True
227wide-226candidate_set_aggregationTrue9.42153943599261True
228wide-227candidate_set_aggregationTrue11.5567368220072241True
229wide-228candidate_set_aggregationTrue9.918552546005231True
230wide-229candidate_set_aggregationTrue10.585735546992511True
231wide-230candidate_set_aggregationTrue10.6934457640018081True
232wide-231candidate_set_aggregationTrue11.3497137160011331True
233wide-232candidate_set_aggregationTrue11.747918780994951True
234wide-233candidate_set_aggregationTrue11.0489462680125141True
235wide-234candidate_set_aggregationTrue11.0145903319935311True
236wide-235candidate_set_aggregationTrue10.424953770008871True
237wide-236candidate_set_aggregationTrue11.6152974020078551True
238wide-237candidate_set_aggregationTrue11.3047625339968361True
239wide-238candidate_set_aggregationTrue12.4946527639986021True
240wide-239candidate_set_aggregationTrue10.8598835899902041True
241wide-240candidate_set_aggregationTrue11.5464065089909131True
242wide-241candidate_set_aggregationTrue9.2452783980115781True
243wide-242candidate_set_aggregationTrue12.0815337810054191True
244wide-243candidate_set_aggregationTrue9.458869214999141True
245wide-244candidate_set_aggregationTrue12.6941617420088731True
246wide-245candidate_set_aggregationTrue8.5725395220069911True
247wide-246candidate_set_aggregationTrue12.8624630949925631True
248wide-247candidate_set_aggregationTrue8.6812353290006291True
249wide-248candidate_set_aggregationTrue14.2884179449902151True
250wide-249conjunctive_disambiguationTrue5.5641517409967491True
251wide-250conjunctive_disambiguationTrue9.572888770999271True
252wide-251conjunctive_disambiguationTrue7.9818972539942481True
253wide-252conjunctive_disambiguationTrue8.6151028300082541True
254wide-253conjunctive_disambiguationTrue7.3437917330011261True
255wide-254conjunctive_disambiguationTrue8.366784912010191True
256wide-255conjunctive_disambiguationTrue6.509432645005291True
257wide-256conjunctive_disambiguationTrue8.8554553510039111True
258wide-257conjunctive_disambiguationTrue6.6254235590022291True
259wide-258conjunctive_disambiguationTrue10.7850428720121271True
260wide-259conjunctive_disambiguationTrue5.2273067339992851True
261wide-260conjunctive_disambiguationTrue9.6026255280012261True
262wide-261conjunctive_disambiguationTrue7.3484767770132751True
263wide-262conjunctive_disambiguationTrue9.6008479279989841True
264wide-263conjunctive_disambiguationTrue7.576629634000711True
265wide-264conjunctive_disambiguationTrue9.0535633420076921True
266wide-265conjunctive_disambiguationTrue7.7012075130041921True
267wide-266conjunctive_disambiguationTrue8.3529367590090261True
268wide-267conjunctive_disambiguationTrue7.66478312700928651True
269wide-268conjunctive_disambiguationTrue7.5131964070023971True
270wide-269conjunctive_disambiguationTrue7.3142714519926811True
271wide-270conjunctive_disambiguationTrue7.2820599410042631True
272wide-271conjunctive_disambiguationTrue7.5533213830058231True
273wide-272conjunctive_disambiguationTrue8.1632461809931561True
274wide-273conjunctive_disambiguationTrue7.8069159869919531True
275wide-274conjunctive_disambiguationTrue8.4577032240049451True
276wide-275conjunctive_disambiguationTrue7.7785824150050761True
277wide-276conjunctive_disambiguationTrue9.0621614190022231True
278wide-277conjunctive_disambiguationTrue7.9604395740025211True
279wide-278conjunctive_disambiguationTrue8.3664610510022611True
280wide-279conjunctive_disambiguationTrue7.29004572299891151True
281wide-280conjunctive_disambiguationTrue7.80310229799943041True
282wide-281conjunctive_disambiguationTrue7.8344502069958251True
283wide-282conjunctive_disambiguationTrue8.43591223799741True
284wide-283conjunctive_disambiguationTrue9.2755765080073621True
285wide-284conjunctive_disambiguationTrue8.0097813190077431True
286wide-285conjunctive_disambiguationTrue10.9371068619948351True
287wide-286conjunctive_disambiguationTrue5.59995356699801051True
288wide-287conjunctive_disambiguationTrue10.8643547679967011True
289wide-288conjunctive_disambiguationTrue5.7596249560010621True
290wide-289negative_lookupTrue7.94278831500560051True
291wide-290negative_lookupTrue5.3735474960121791True
292wide-291negative_lookupTrue7.4239207179925871True
293wide-292negative_lookupTrue2.9296528190025131True
294wide-293negative_lookupTrue5.8564246629975971True
295wide-294negative_lookupTrue7.0530814379890221True
296wide-295negative_lookupTrue6.6658418680017351True
297wide-296negative_lookupTrue7.3098676249937851True
298wide-297negative_lookupTrue6.2655424630065681True
299wide-298negative_lookupTrue7.07434265699703251True
300wide-299negative_lookupTrue5.5073146859940611True
301wide-300negative_lookupTrue5.6934185839927521True
302wide-301negative_lookupTrue5.4914943999901881True
303wide-302negative_lookupTrue4.5116761920071441True
304wide-303negative_lookupTrue5.6795986420038391True
305wide-304negative_lookupTrue5.1758819379901981True
306wide-305negative_lookupTrue7.6127283660025571True
307wide-306negative_lookupTrue5.3825003679958171True
308wide-307negative_lookupTrue7.8189000880083771True
309wide-308negative_lookupTrue5.6747006010118641True
310wide-309negative_lookupTrue8.506532022991451True
311wide-310negative_lookupTrue3.1429941890091871True
312wide-311negative_lookupTrue7.01214635100041051True
313wide-312negative_lookupTrue2.93773422599770131True
314wide-313negative_lookupTrue6.3316445539967391True
315wide-314negative_lookupTrue3.3771582790068351True
316wide-315negative_lookupTrue5.1428850449883611True
317wide-316negative_lookupTrue5.3712708890088831True
318wide-317negative_lookupTrue6.4654258410009791True
319wide-318negative_lookupTrue2.89972448399930731True
320wide-319negative_lookupTrue5.7624612070067091True
321wide-320negative_lookupTrue5.029174277005951True