domains / families / research / sigcomm-experiments

sigcomm-experiments

separate

Use when designing or auditing ACM SIGCOMM experiments — climbing the evidence ladder from microbenchmarks to testbed and trace replay to deployment, choosing baselines that match the deployed state of the art, reporting tail percentiles and variance over repeated trials, mapping break points, and holding the fair variable fixed.

When to use

• designing ACM SIGCOMM experiments
• auditing ACM SIGCOMM experiments
• climbing the evidence ladder
• choosing baselines
• reporting tail percentiles and variance
• mapping break points
• holding the fair variable fixed

When not to use

• tasks not related to ACM SIGCOMM experiments

Skill page

Source