Introduces CaTS-Bench with human gold-standard captions and a synthetic generation pipeline to evaluate vision-language models on time series captioning and numeric reasoning.
answer": <string>} <string>must be an answer string containing only A, B. Ensure your output parses as JSON with exactly one top-level object containing the answer field. Answer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CaTS-Bench: Can Language Models Describe Time Series?
Introduces CaTS-Bench with human gold-standard captions and a synthetic generation pipeline to evaluate vision-language models on time series captioning and numeric reasoning.