READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis
Quick summary
arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through downstream prediction. We introduce READ-Bench, a benchmark for historical-case retrieval across 12 diagnostic datasets, centered on multivariate time series, that defines relevance by shared fault or event type rather than signal shape, so visually different traces of the same fault count as relevant while similar-looking traces of different faults do not. Treating retrieval as a base retriever
Key takeaways
- arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through downstream prediction.
- We introduce READ-Bench, a benchmark for historical-case retrieval across 12 diagnostic datasets, centered on multivariate time series, that defines relevance by shared fault or event type rather than signal shape, so visually different traces of the same fault count as relevant while similar-looking traces of different faults do not.
- Treating retrieval as a base retriever
Why it matters
“READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments