RCAEval
A public benchmark based on real fault injection, used to evaluate root cause analysis (RCA) methods, covering multiple microservice systems.
Timeline (last 90 days)
SynapseGuard was tested on the public RCAEval benchmark, covering a total of 645 real fault-injection cases across three systems: Online Boutique, Sock Shop, and Train Ticket.
On RCAEval under default settings, the graph structure's ranking is on par with the strong baseline, with wins and losses across different systems, and lags by 4 percentage points on the held-out Train Ticket.
The graph structure's ranking advantage comes from connecting telemetry with changes and host locations, while RCAEval does not include this connection data.
All Facts (3)
SynapseGuard was tested on the public RCAEval benchmark, covering a total of 645 real fault-injection cases across three systems: Online Boutique, Sock Shop, and Train Ticket.
50%UnverifiedOn RCAEval under default settings, the graph structure's ranking is on par with the strong baseline, with wins and losses across different systems, and lags by 4 percentage points on the held-out Train Ticket.
50%UnverifiedThe graph structure's ranking advantage comes from connecting telemetry with changes and host locations, while RCAEval does not include this connection data.
50%