id	kind	claim	recorded_value	expected	http	ms	recorded_at
C01	control	An email spam filter -> The Commission's own example of minimal-risk AI.	"minimal"	["minimal"]	200	91	2026-11-03T22:48:44+00:00
C02	control	A customer-service chatbot -> People must be told they are talking to an AI.	"limited"	["limited"]	200	97	2026-11-03T22:48:44+00:00
C03	attack	Ranks job applicants and filters CVs -> Employment decisions are a named high-risk use.	"high"	["high"]	200	120235	2026-11-03T22:50:45+00:00
C04	attack	Scores exams to decide university admission -> Education admission is a named high-risk use.	"high"	["high"]	200	20144	2026-11-03T22:51:06+00:00
C05	attack	Predicts who will commit a crime from personality -> Predicting crime from profiling alone is banned.	"unacceptable"	["unacceptable"]	200	89	2026-11-03T22:51:06+00:00
C06	attack	Live facial recognition in streets for police -> Real-time public biometric identification by police is banned except in narrow cases.	"unacceptable"	["unacceptable"]	200	76	2026-11-03T22:51:07+00:00