In an industrial dataset evaluation, SBLD produced a statistically significant reduction in the effort required to identify all failure-relevant events in a failing run.
Notes on verification
Confirmed by peer-reviewed paper (ESEM 2020) and independently corroborated by ACM DL abstract and DeepAI mirror; full text specifies Wilcoxon signed-rank test significance for effort reduction versus baseline comparisons.
Sources
- Spectrum-Based Log Diagnosis (arxiv.org)
- https://dl.acm.org/doi/10.1145/3382494.3410684 (dl.acm.org)
- https://deepai.org/publication/spectrum-based-log-diagnosis (deepai.org)