dp-zp-agent/experiments/graphrag/results/answers_v7_regression_2026-10-26/answers_regression.csv

20 KiB

1idcategorystricterrorlatency_secondsattemptsfirst_pass_strict
2wide-001shared_keyword_pairTrue5.2623787490010731True
3wide-002shared_keyword_pairTrue11.0238447880110471True
4wide-003shared_keyword_pairTrue6.8371123709948731True
5wide-004shared_keyword_pairTrue7.8250736180052631True
6wide-005shared_keyword_pairTrue10.0471339920040921True
7wide-006shared_keyword_pairTrue8.645936296990841True
8wide-007shared_keyword_pairTrue9.6618236869981051True
9wide-008shared_keyword_pairTrue8.5334321900008941True
10wide-009shared_keyword_pairTrue8.8527850499958731True
11wide-010shared_keyword_pairTrue8.6753802360035481True
12wide-011shared_keyword_pairTrue9.1789059399889081True
13wide-012shared_keyword_pairTrue8.796270100996481True
14wide-013shared_keyword_pairTrue9.1175401719956431True
15wide-014shared_keyword_pairTrue8.6152187200059421True
16wide-015shared_keyword_pairTrue9.3953879790060451True
17wide-016shared_keyword_pairTrue8.7794549389946041True
18wide-017shared_keyword_pairTrue9.4785776789940431True
19wide-018shared_keyword_pairTrue8.6809339920000641True
20wide-019shared_keyword_pairTrue9.2400193159992341True
21wide-020shared_keyword_pairTrue8.5304380040033721True
22wide-021shared_keyword_pairTrue9.0190070349926831True
23wide-022shared_keyword_pairTrue8.5984874360001411True
24wide-023shared_keyword_pairTrue9.1860677460063021True
25wide-024shared_keyword_pairTrue8.590942956012441True
26wide-025shared_keyword_pairTrue8.7225916660099761True
27wide-026shared_keyword_pairTrue8.6840578109986381True
28wide-027shared_keyword_pairTrue8.909655385999941True
29wide-028shared_keyword_pairTrue9.0364313559985021True
30wide-029shared_keyword_pairTrue16.9859412079968022False
31wide-030shared_keyword_pairTrue9.2787656590080591True
32wide-031shared_keyword_pairTrue8.8597970609989721True
33wide-032shared_keyword_pairTrue8.5517122810124421True
34wide-033shared_keyword_pairTrue8.8716598739993061True
35wide-034shared_keyword_pairTrue10.277132561997861True
36wide-035shared_keyword_pairTrue8.7318082470010271True
37wide-036shared_keyword_pairTrue10.0222447889973411True
38wide-037shared_keyword_pairTrue7.6069504299957771True
39wide-038shared_keyword_pairTrue9.0735493340034741True
40wide-039shared_keyword_pairTrue6.6499410589894981True
41wide-040shared_keyword_pairTrue9.700094435000211True
42wide-041same_academic_year_pairTrue4.96461352199548861True
43wide-042same_academic_year_pairTrue8.7396533480059591True
44wide-043same_academic_year_pairTrue8.060106357996121True
45wide-044same_academic_year_pairTrue10.402209178995691True
46wide-045same_academic_year_pairTrue8.448390038000071True
47wide-046same_academic_year_pairTrue9.6357051619997951True
48wide-047same_academic_year_pairTrue11.8220986780070231True
49wide-048same_academic_year_pairTrue8.1487097330100371True
50wide-049same_academic_year_pairTrue18.1295303420047282False
51wide-050same_academic_year_pairTrue8.2489696239936171True
52wide-051same_academic_year_pairTrue10.2770829960063571True
53wide-052same_academic_year_pairTrue10.2816550370043841True
54wide-053same_academic_year_pairTrue5.8981936399941331True
55wide-054same_academic_year_pairTrue7.9091744769975781True
56wide-055same_academic_year_pairTrue6.1914005949947751True
57wide-056same_academic_year_pairTrue10.2299512750032591True
58wide-057same_academic_year_pairTrue5.8589028649876131True
59wide-058same_academic_year_pairTrue9.3908822329976831True
60wide-059same_academic_year_pairTrue7.2878930860024411True
61wide-060same_academic_year_pairTrue10.0455470639863051True
62wide-061same_academic_year_pairTrue7.134985942000641True
63wide-062same_academic_year_pairTrue8.9946017809998011True
64wide-063same_academic_year_pairTrue6.2881579660024731True
65wide-064same_academic_year_pairTrue9.0255552269954931True
66wide-065same_academic_year_pairTrue6.96506473100453151True
67wide-066same_academic_year_pairTrue9.5747805790015261True
68wide-067same_academic_year_pairTrue8.0740114759973951True
69wide-068same_academic_year_pairTrue9.5316115189925771True
70wide-069same_academic_year_pairTrue8.6345102070044961True
71wide-070same_academic_year_pairTrue8.9584000350005231True
72wide-071same_academic_year_pairTrue9.778397539994331True
73wide-072same_academic_year_pairTrue8.3664471990050521True
74wide-073same_academic_year_pairTrue9.7569758189929421True
75wide-074same_academic_year_pairTrue7.2324087300075921True
76wide-075same_academic_year_pairTrue9.7651646239974071True
77wide-076same_academic_year_pairTrue7.2853139930084581True
78wide-077same_academic_year_pairTrue10.1519192889973061True
79wide-078same_academic_year_pairTrue7.6733784410025691True
80wide-079same_academic_year_pairTrue10.6348931579996131True
81wide-080same_academic_year_pairTrue4.7895006159960761True
82wide-081same_start_year_pairTrue8.5850489849981391True
83wide-082same_start_year_pairTrue8.4994047910004161True
84wide-083same_start_year_pairTrue5.6304028209997341True
85wide-084same_start_year_pairTrue6.9086549189960351True
86wide-085same_start_year_pairTrue5.9448167769878641True
87wide-086same_start_year_pairTrue9.1260758619901031True
88wide-087same_start_year_pairTrue5.4408620129979681True
89wide-088same_start_year_pairTrue6.50593000999651851True
90wide-089same_start_year_pairTrue6.6971578609955031True
91wide-090same_start_year_pairTrue3.262026362994221True
92wide-091same_start_year_pairTrue6.43983820799621751True
93wide-092same_start_year_pairTrue9.0664953959931151True
94wide-093same_start_year_pairTrue7.3601522719982311True
95wide-094same_start_year_pairTrue9.5412698900036051True
96wide-095same_start_year_pairTrue7.5694378590123961True
97wide-096same_start_year_pairTrue11.0242704230040541True
98wide-097same_start_year_pairTrue5.7154820769937941True
99wide-098same_start_year_pairTrue8.7363716319960081True
100wide-099same_start_year_pairTrue6.2494469249941181True
101wide-100same_start_year_pairTrue10.8058126490068391True
102wide-101same_start_year_pairTrue5.2202767949929691True
103wide-102same_start_year_pairTrue9.9475602190068461True
104wide-103same_start_year_pairTrue7.7799311540002241True
105wide-104same_start_year_pairTrue10.8908184300089491True
106wide-105same_start_year_pairTrue3.65451748399937061True
107wide-106same_start_year_pairTrue7.74199466199206651True
108wide-107same_start_year_pairTrue4.4109952389990211True
109wide-108same_start_year_pairTrue6.5837893860007171True
110wide-109same_start_year_pairTrue6.9585907959990441True
111wide-110same_start_year_pairTrue11.6485790769947931True
112wide-111same_start_year_pairTrue3.0221863209881121True
113wide-112same_start_year_pairTrue2.67442680700332861True
114wide-113person_title_yearTrue3.90019846201175821True
115wide-114person_title_yearTrue6.900904622001691True
116wide-115person_title_yearTrue5.27743540599476551True
117wide-116person_title_yearTrue5.4052270450047221True
118wide-117person_title_yearTrue4.6626881020056321True
119wide-118person_title_yearTrue4.65983350299939051True
120wide-119person_title_yearTrue7.6073767000052611True
121wide-120person_title_yearTrue3.5516286030033371True
122wide-121person_title_yearTrue6.1793112680024931True
123wide-122person_title_yearTrue5.9171003249939531True
124wide-123person_title_yearTrue6.5480461299885061True
125wide-124person_title_yearTrue7.8617386890109631True
126wide-125person_title_yearTrue4.5639626079937441True
127wide-126person_title_yearTrue5.808280943994761True
128wide-127person_title_yearTrue5.0771051019983131True
129wide-128person_title_yearTrue6.0384645800077121True
130wide-129person_title_yearTrue7.0968729890009851True
131wide-130person_title_yearTrue7.8725255530007422False
132wide-131person_title_yearTrue7.4989217999973331True
133wide-132person_title_yearTrue5.8925311380007771True
134wide-133person_title_yearTrue5.66381279200140851True
135wide-134person_title_yearTrue5.1722512340056711True
136wide-135person_title_yearTrue5.7443714000110051True
137wide-136person_title_yearTrue4.7988297929987311True
138wide-137person_keyword_titleTrue6.9103177150100241True
139wide-138person_keyword_titleTrue6.9130081769981191True
140wide-139person_keyword_titleTrue8.6559448699990751True
141wide-140person_keyword_titleTrue7.7736926590005171True
142wide-141person_keyword_titleTrue9.6244331869966121True
143wide-142person_keyword_titleTrue3.8448123939888321True
144wide-143person_keyword_titleTrue7.3119626709958541True
145wide-144person_keyword_titleTrue8.9964153960027031True
146wide-145person_keyword_titleTrue4.761727835008061True
147wide-146person_keyword_titleTrue6.7106669159984451True
148wide-147person_keyword_titleTrue7.2002400369965471True
149wide-148person_keyword_titleTrue8.8730948919983351True
150wide-149person_keyword_titleTrue7.563196960007191True
151wide-150person_keyword_titleTrue8.9752149900014051True
152wide-151person_keyword_titleTrue7.5378571220062441True
153wide-152person_keyword_titleTrue8.621676951006521True
154wide-153person_keyword_titleTrue6.8114679410064131True
155wide-154person_keyword_titleTrue9.1362206789926861True
156wide-155person_keyword_titleTrue7.4902419130085041True
157wide-156person_keyword_titleTrue9.6194242359924831True
158wide-157person_keyword_titleTrue7.0756995819974691True
159wide-158person_keyword_titleTrue9.4027727619977671True
160wide-159person_keyword_titleTrue7.39261557000281751True
161wide-160person_keyword_titleTrue9.5922192720026941True
162wide-161person_keyword_titleTrue7.6929304700024661True
163wide-162person_keyword_titleTrue9.3369596470001851True
164wide-163person_keyword_titleTrue7.6591459079936611True
165wide-164person_keyword_titleTrue9.9898200020106741True
166wide-165person_keyword_titleTrue3.67578762400080451True
167wide-166person_keyword_titleTrue6.715454035002041True
168wide-167person_keyword_titleTrue8.4532329069916161True
169wide-168person_keyword_titleTrue7.7899372200045041True
170wide-169document_author_category_multi_hopTrue8.2301463040057571True
171wide-170document_author_category_multi_hopTrue6.49323321400152051True
172wide-171document_author_category_multi_hopTrue7.0966075299947991True
173wide-172document_author_category_multi_hopTrue5.5937652330030691True
174wide-173document_author_category_multi_hopTrue6.8066008659952791True
175wide-174document_author_category_multi_hopTrue5.35368781400029551True
176wide-175document_author_category_multi_hopTrue7.0724157299991931True
177wide-176document_author_category_multi_hopTrue6.4186875989980761True
178wide-177document_author_category_multi_hopTrue7.7686412750044841True
179wide-178document_author_category_multi_hopTrue6.6956706350028981True
180wide-179document_author_category_multi_hopTrue6.6467371920007281True
181wide-180document_author_category_multi_hopTrue5.9890187920100291True
182wide-181document_author_category_multi_hopTrue6.1194988930074031True
183wide-182document_author_category_multi_hopTrue5.97459919701213951True
184wide-183document_author_category_multi_hopTrue6.0771261529880581True
185wide-184document_author_category_multi_hopTrue5.9924358529970051True
186wide-185document_author_category_multi_hopTrue6.2132225649984321True
187wide-186document_author_category_multi_hopTrue6.6839543609967221True
188wide-187document_author_category_multi_hopTrue6.8433289060048991True
189wide-188document_author_category_multi_hopTrue7.072580836000271True
190wide-189document_author_category_multi_hopTrue6.2599522890086521True
191wide-190document_author_category_multi_hopTrue6.5052969759999541True
192wide-191document_author_category_multi_hopTrue6.2686398369987731True
193wide-192document_author_category_multi_hopTrue7.0033987920032811True
194wide-193person_multiple_categoriesTrue6.1948558029980631True
195wide-194person_multiple_categoriesTrue5.3644374540017451True
196wide-195person_multiple_categoriesTrue4.5452867519925351True
197wide-196person_multiple_categoriesTrue4.1513376410002821True
198wide-197person_multiple_categoriesTrue8.1465579499927122False
199wide-198person_multiple_categoriesTrue4.2333870410075181True
200wide-199person_multiple_categoriesTrue6.2919385120039811True
201wide-200person_multiple_categoriesTrue9.2578442470112352False
202wide-201person_multiple_categoriesTrue3.86063351700431671True
203wide-202person_multiple_categoriesTrue4.7069028870027981True
204wide-203person_multiple_categoriesTrue4.97163771100167651True
205wide-204person_multiple_categoriesTrue11.9509999519941632False
206wide-205person_multiple_categoriesTrue5.601922433997971True
207wide-206person_multiple_categoriesTrue5.5909881940024211True
208wide-207person_multiple_categoriesTrue7.8463796550058762False
209wide-208person_multiple_categoriesTrue7.0503302170109241True
210wide-209person_multiple_categoriesTrue5.9817901880014691True
211wide-210person_multiple_categoriesTrue4.0149294010043381True
212wide-211person_multiple_categoriesTrue5.0482576270005671True
213wide-212person_multiple_categoriesTrue2.7276441059948411True
214wide-213person_multiple_categoriesTrue4.5873786029987971True
215wide-214person_multiple_categoriesTrue3.66405946800659881True
216wide-215person_multiple_categoriesTrue7.1653787719988031True
217wide-216person_multiple_categoriesTrue6.9136480239976662False
218wide-217candidate_set_aggregationTrue8.1494360009965021True
219wide-218candidate_set_aggregationTrue7.9282233249978161True
220wide-219candidate_set_aggregationTrue8.2993626899988161True
221wide-220candidate_set_aggregationTrue9.4507919570023661True
222wide-221candidate_set_aggregationTrue8.8328465709928421True
223wide-222candidate_set_aggregationTrue9.5678840839973421True
224wide-223candidate_set_aggregationTrue8.8383878460008421True
225wide-224candidate_set_aggregationTrue9.3861600629898021True
226wide-225candidate_set_aggregationTrue8.624943253991661True
227wide-226candidate_set_aggregationTrue9.4282729849946921True
228wide-227candidate_set_aggregationTrue8.5992487330076981True
229wide-228candidate_set_aggregationTrue9.4870152020012031True
230wide-229candidate_set_aggregationTrue8.6053838070074561True
231wide-230candidate_set_aggregationTrue9.610598594998011True
232wide-231candidate_set_aggregationTrue8.8230518130003471True
233wide-232candidate_set_aggregationTrue9.7409537069906951True
234wide-233candidate_set_aggregationTrue8.7223864839907041True
235wide-234candidate_set_aggregationTrue9.4896448869985761True
236wide-235candidate_set_aggregationTrue8.5599140670092311True
237wide-236candidate_set_aggregationTrue9.5241887740121461True
238wide-237candidate_set_aggregationTrue8.787024751989521True
239wide-238candidate_set_aggregationTrue9.7795899210032081True
240wide-239candidate_set_aggregationTrue8.8322120220109351True
241wide-240candidate_set_aggregationTrue9.9791314979956951True
242wide-241candidate_set_aggregationTrue8.594882228004281True
243wide-242candidate_set_aggregationTrue9.8237191049993271True
244wide-243candidate_set_aggregationTrue8.2200466200010851True
245wide-244candidate_set_aggregationTrue10.1945053840026961True
246wide-245candidate_set_aggregationTrue8.1946348530036631True
247wide-246candidate_set_aggregationTrue10.072407255996951True
248wide-247candidate_set_aggregationTrue7.76127890299541True
249wide-248candidate_set_aggregationTrue11.5602600200072631True
250wide-249conjunctive_disambiguationTrue5.4765918799967041True
251wide-250conjunctive_disambiguationTrue8.8434674029995221True
252wide-251conjunctive_disambiguationTrue7.1154502010031141True
253wide-252conjunctive_disambiguationTrue8.4161700429976921True
254wide-253conjunctive_disambiguationTrue6.9203644500084921True
255wide-254conjunctive_disambiguationTrue8.2490185740025481True
256wide-255conjunctive_disambiguationTrue6.8584850640036171True
257wide-256conjunctive_disambiguationTrue8.3363302719953941True
258wide-257conjunctive_disambiguationTrue6.962147887010361True
259wide-258conjunctive_disambiguationTrue8.3813033940095921True
260wide-259conjunctive_disambiguationTrue7.0459150520036931True
261wide-260conjunctive_disambiguationTrue8.7216103490063691True
262wide-261conjunctive_disambiguationTrue6.9355969200114491True
263wide-262conjunctive_disambiguationTrue8.7767317800025921True
264wide-263conjunctive_disambiguationTrue6.7599109349976061True
265wide-264conjunctive_disambiguationTrue9.7992475520004521True
266wide-265conjunctive_disambiguationTrue5.1894807119970211True
267wide-266conjunctive_disambiguationTrue8.859791519993451True
268wide-267conjunctive_disambiguationTrue6.75240944200777451True
269wide-268conjunctive_disambiguationTrue9.2913880999985851True
270wide-269conjunctive_disambiguationTrue6.5669829840044261True
271wide-270conjunctive_disambiguationTrue8.4169235239969571True
272wide-271conjunctive_disambiguationTrue6.7006995919946351True
273wide-272conjunctive_disambiguationTrue8.5311220639996461True
274wide-273conjunctive_disambiguationTrue6.8685410539910661True
275wide-274conjunctive_disambiguationTrue8.5852976290043441True
276wide-275conjunctive_disambiguationTrue6.8739425300009321True
277wide-276conjunctive_disambiguationTrue8.5943468339974061True
278wide-277conjunctive_disambiguationTrue6.8160389670083531True
279wide-278conjunctive_disambiguationTrue8.5913394340022931True
280wide-279conjunctive_disambiguationTrue6.78249739500461151True
281wide-280conjunctive_disambiguationTrue8.6976707330031791True
282wide-281conjunctive_disambiguationTrue6.7628428229945711True
283wide-282conjunctive_disambiguationTrue8.6473532139934831True
284wide-283conjunctive_disambiguationTrue18.085952175999412False
285wide-284conjunctive_disambiguationTrue7.2011677340051391True
286wide-285conjunctive_disambiguationFalse28.018320786010012False
287wide-286conjunctive_disambiguationTrue5.1586368069984021True
288wide-287conjunctive_disambiguationTrue11.1815340399916751True
289wide-288conjunctive_disambiguationTrue5.3757843529892851True
290wide-289negative_lookupTrue3.15197800799796821True
291wide-290negative_lookupTrue2.56526101699273571True
292wide-291negative_lookupTrue2.1169325020018731True
293wide-292negative_lookupTrue2.15222212199296341True
294wide-293negative_lookupTrue2.21852705799392421True
295wide-294negative_lookupTrue2.35941863199695941True
296wide-295negative_lookupTrue3.49916697900334841True
297wide-296negative_lookupTrue3.3093623180029681True
298wide-297negative_lookupTrue3.12189936800859871True
299wide-298negative_lookupTrue2.71419885000796061True
300wide-299negative_lookupTrue2.44477322099555751True
301wide-300negative_lookupTrue2.5791827360080791True
302wide-301negative_lookupTrue2.4257724790077191True
303wide-302negative_lookupTrue2.56222036099643451True
304wide-303negative_lookupTrue2.4769812980084681True
305wide-304negative_lookupTrue2.60079433000646531True
306wide-305negative_lookupTrue2.4577863579906991True
307wide-306negative_lookupTrue2.5664863359997981True
308wide-307negative_lookupTrue2.61695595500350461True
309wide-308negative_lookupTrue2.73404198599746451True
310wide-309negative_lookupTrue2.6198043149925071True
311wide-310negative_lookupTrue2.5561219109949891True
312wide-311negative_lookupTrue2.43173230600950771True
313wide-312negative_lookupTrue2.5068491720012391True
314wide-313negative_lookupTrue2.41416542200022381True
315wide-314negative_lookupTrue2.48778455800493251True
316wide-315negative_lookupTrue2.47708660700300241True
317wide-316negative_lookupTrue2.4942391550139291True
318wide-317negative_lookupTrue2.4618244820012481True
319wide-318negative_lookupTrue2.43531191498914271True
320wide-319negative_lookupTrue2.5129337130056231True
321wide-320negative_lookupTrue1.83795923700381541True