Research map / Time series / Foundation models for time series
Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
Zhao Tan, Yiji Zhao, Shiyu Wang, Chang Xu, Yuxuan Liang, Xiping Liu, Shirui Pan, Ming Jin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add self-correction loop (ablation) | Sonar-TS · NLQTSBench Sliding Window | score: 0.7250 -> 0.7827 | Improved |
| add self-correction loop (ablation) | Sonar-TS · NLQTSBench Average | score: 0.5930 -> 0.6144 | Improved |
| add feature tables (SAX index) (ablation) | Sonar-TS · NLQTSBench Shape Identification | score: 0.1561 -> 0.3336 | Improved |
| add feature tables (SAX index) (ablation) | Sonar-TS · NLQTSBench Composite Trend | score: 0.0422 -> 0.2988 | Improved |
| add feature tables (SAX index) (ablation) | Sonar-TS · NLQTSBench Periodicity Detection | score: 0.8804 -> 0.8625 | Hurt |
| add experiences (prompt cold start) (ablation) | Sonar-TS · NLQTSBench Contextual Anomaly | score: 0.2501 -> 0.4767 | Improved |
| add experiences (prompt cold start) (ablation) | Sonar-TS · NLQTSBench Insight Synthesis | score: 0.3415 -> 0.7395 | Improved |
| add experiences (prompt cold start) (ablation) | Sonar-TS · NLQTSBench Average | score: 0.4686 -> 0.6144 | Improved |
| add Python verification (ablation) | Sonar-TS · NLQTSBench Periodicity Detection | score: 0.0154 -> 0.8625 | Improved |
| add Python verification (ablation) | Sonar-TS · NLQTSBench Subsequence Matching | score: 0.0396 -> 0.9439 | Improved |
| add Python verification (ablation) | Sonar-TS · NLQTSBench Average | score: 0.2721 -> 0.6144 | Improved |
| add Python verification (ablation) | Sonar-TS · NLQTSBench Atomic Retrieval | score: 0.8294 -> 0.8609 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ITFormer-7B — ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset (ICML 2025) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- LAST SToP for Modeling Asynchronous Time Series (ICML 2025 · similarity 0.84)
- TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval (NeurIPS 2025 · similarity 0.84)
- ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset (ICML 2025 · similarity 0.83)
- CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation (AAAI 2025 · similarity 0.83)
- TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning (NeurIPS 2026 · similarity 0.83)
- Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
