The question
Can mergeable summaries improve accuracy, memory or update cost for a narrowly defined streaming statistic?
This is a proposed research direction. No novel algorithm, completed benchmark or performance gain is claimed.
Why it matters
Observability, analytics and monitoring systems could summarize high-volume streams more efficiently.
Search space
Sketch layouts, update rules, merge strategies and support for windows or deletions.
What would count as progress?
- Error against exact results
- memory
- update/merge speed
- repeated-seed behavior
- adversarial-input tests.
A useful result improves a measured trade-off against strong baselines on held-out workloads, with reproducible code and documented limitations.
Baselines and boundaries
Choose one statistic first. Compare KLL/REQ for quantiles or appropriate cardinality/heavy-hitter methods. Distinguish rank error from value error; empirical tests do not establish a theoretical guarantee.
Starting reference
Where you could contribute
Help define representative, legally shareable workloads; critique the correctness contract; implement baselines; propose candidates; or reproduce measurements. Negative results and failure cases are useful contributions.
A detailed research brief is being prepared. Access requests will become available when that brief and the request service are ready.