# DiffNator: Generating Structured Explanations of Time-Series Differences

arXiv: https://arxiv.org/abs/2509.20007 · HTML: https://mlsanity.com/paper/2509.20007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [VisText: A Benchmark for Semantically Rich Chart Captioning](https://mlsanity.com/paper/2307.05356/) (2023)
- [ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning](https://mlsanity.com/paper/2412.03104/) (2024)
- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model](https://mlsanity.com/paper/2010.09142/) (2020)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset](https://mlsanity.com/paper/2506.20093/) (2025)
- [LineCap: Line Charts for Data Visualization Captioning Models](https://mlsanity.com/paper/2207.07243/) (2022)
- [Domain-Independent Automatic Generation of Descriptive Texts for Time-Series Data](https://mlsanity.com/paper/2409.16647/) (2024)
- [XForecast: Evaluating Natural Language Explanations for Time Series Forecasting](https://mlsanity.com/paper/2410.14180/) (2024)

## Abstract (arXiv)

In many IoT applications, the central interest lies not in individual sensor signals but in their differences, yet interpreting such differences requires expert knowledge. We propose DiffNator, a framework for structured explanations of differences between two time series. We first design a JSON schema that captures the essential properties of such differences. Using the Time-series Observations of Real-world IoT (TORI) dataset, we generate paired sequences and train a model that combine a time-series encoder with a frozen LLM to output JSON-formatted explanations. Experimental results show that DiffNator generates accurate difference explanations and substantially outperforms both a visual question answering (VQA) baseline and a retrieval method using a pre-trained time-series encoder.