Metraipolis › archive › dc_2c89904f179b
Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability — arXiv:2610.05686
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05686
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:18.138Z
- SHA-256 of the archived text
dbc944a6a7db73052e2dc5a9665ea5d09c7aeec3070301dbc3e82e04062fe5a5- Stable URL of this page
https://metraipolis.com/documento/dc_2c89904f179b
How to cite
Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability — arXiv:2610.05686 — arXiv, https://arxiv.org/abs/2610.05686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c89904f179b (Metraipolis archive dc_2c89904f179b, sha256 dbc944a6a7db73052e2dc5a9665ea5d09c7aeec3070301dbc3e82e04062fe5a5)
BibTeX
@misc{dc2c89904f179b,
title = {Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability — arXiv:2610.05686},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05686},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c89904f179b; sha256 dbc944a6a7db73052e2dc5a9665ea5d09c7aeec3070301dbc3e82e04062fe5a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In recent years, time-series question answering (QA) systems have made significant progress. However, generating a correct answer does not show whether retaining the supplied numerical series improves task performance, nor whether the prediction is sensitive to changes in that input. While some systems provide rationales, answer accuracy also does not show whether their numerical claims are grounded in the supplied series or whether the stated inference is valid. In this work, we focus on evaluating four time-series QA systems: TimeOmni-1, ChatTS, TimeOmni-VL, and Time-MQA. First, for three systems with released evaluation data, we reproduce their reported results and compare the performance of the systems with their backbones. Then, we introduce a benchmark named COMMON-TSQA, which collects public evaluation datasets from existing time-series benchmarks and unifies their sample representation, task definitions, and answer schemas, while evaluating each system through its own interface under common evaluation criteria. The evaluation uses the original condition and six interventions while keeping the question and target fixed. Our analysis shows that aggregate performance alone can obscure how systems use numerical evidence. Similar task-level scores can arise despite substantial changes in individual predictions. Some interventions induce simple fallback behavior rather than preserved task ability. We also evaluate rationales for factual grounding, inference validity, and consistency with the final answer. We find that rationales often contain time-series claims unsupported by the input. Moreover, the rationale audit shows that agreement between a rationale and its final answer can coexist with incorrect numerical descriptions or invalid intermediate inferences. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.05686 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:05.620Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).