What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions

• URL: http://arxiv.org/abs/2605.14422v1
• Date: Thu, 14 May 2026 06:10:23 GMT
• Title: What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
• Abstract summary: Time series forecasting has become increasingly critical in real-world scenarios.<n>Traditional methods typically rely on historical data or factual future conditions.<n>We introduce the task of counterfactual time series forecasting with textual conditions.
• Score: 17.093435375113298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to complex and stochastic future conditions, which introduces fundamental challenges in both forecasting and evaluation. Traditional methods typically rely on historical data or factual future conditions, while overlooking counterfactual scenarios. Furthermore, many existing approaches are restricted to simple structured conditions, limiting their ability to generalize to the real-world complexities. To address these gaps, we introduce the task of counterfactual time series forecasting with textual conditions, enabling more flexible and condition-aware forecasting. We propose a comprehensive evaluation framework that encompasses both factual and counterfactual settings, even in the absence of ground truth time series. Additionally, we present a novel text-attribution mechanism that distinguishes mutable from immutable factors, thereby improving forecast accuracy under sophisticated and stochastic textual conditions. The project page is at https://seqml.github.io/TADiff/

Related papers

• OutageDiT: A Generative Foundation Model for Power Outage Forecasting and Scenario Simulation [15.111545350167729]
  OutageDiT is a foundation model for generating seven-day outage trajectories at quarter-hour resolution.<n>Condition encoder processes the historical context and known future co variables once per forecast.<n> shallow flow decoder reuses the resulting horizon-aligned states to generate complete trajectories.
  arXiv  Detail & Related papers  (2026-09-01T21:54:17Z)
• ConTex: Reformulating Counterfactual Generation For Time Series Forecasting [11.467075353374478]
  Decision-making with deep learning-based time series forecasting requires actionable insights.<n>Counterfactual Time Series Explanations (ConTex) is a model-agnostic, decomposed architecture comprising a temporal context encoder and a conditional encoder.<n>Our approach reduces computational cost by at least 12-36x compared to instance-wise generation and supports real-time inference at approximately 0.007 seconds.
  arXiv  Detail & Related papers  (2026-06-16T15:25:12Z)
• Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting [15.993594186846826]
  Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling.<n>Timeflies is a unified framework that reformulates forecasting as a joint problem of future observability inference and value estimation.
  arXiv  Detail & Related papers  (2026-06-11T16:59:42Z)
• Nexus : An Agentic Framework for Time Series Forecasting [72.73790673303154]
  Time series forecasting requires reasoning with unstructured contextual data such as news or events.<n>We introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages.<n>We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized.
  arXiv  Detail & Related papers  (2026-05-14T05:12:13Z)
• TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks [12.114998959919978]
  It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions.<n>We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively richer informational settings.<n>By controlling access to future targets and contextual information, the benchmark enables a diagnostic analysis of whether models can correctly interpret temporal patterns.
  arXiv  Detail & Related papers  (2026-02-05T01:02:19Z)
• What If TSF: A Benchmark for Reframing Forecasting as Scenario-Guided Multimodal Forecasting [8.593646221015264]
  What If TSF (WIT) is a benchmark designed to evaluate whether models can condition their forecasts on contextual text.<n>WIT offers a rigorous testbed for scenario-guided multimodal forecasting.
  arXiv  Detail & Related papers  (2026-01-13T12:47:43Z)
• EventTSF: Event-Aware Non-Stationary Time Series Forecasting [73.54313384419792]
  EventTSF is an autoregressive generation framework that integrates historical time series with textual events to make subsequent forecasts.<n>Experiments on 8 synthetic and real-world datasets show that EventTSF outperforms 12 baselines across diverse event-aware non-stationary time series forecasting scenarios.
  arXiv  Detail & Related papers  (2025-08-19T01:28:47Z)
• When Does Multimodality Lead to Better Time Series Forecasting? [96.26052272121615]
  We investigate whether and under what conditions such multimodal integration consistently yields gains.<n>Our findings reveal that the benefits of multimodality are highly condition-dependent.<n>Our study offers a rigorous, quantitative foundation for understanding when multimodality can be expected to aid forecasting tasks.
  arXiv  Detail & Related papers  (2025-06-20T23:55:56Z)
• Sundial: A Family of Highly Capable Time Series Foundation Models [47.27032162475962]
  We introduce Sundial, a family of native, flexible, and scalable time series foundation models.<n>Our models are pre-trained without specifying any prior distribution and can generate multiple probable predictions.<n>Sundial achieves state-of-the-art results on both point and probabilistic forecasting benchmarks with a just-in-time inference speed.
  arXiv  Detail & Related papers  (2025-02-02T14:52:50Z)
• SCTc-TE: A Comprehensive Formulation and Benchmark for Temporal Event Forecasting [63.01035584154509]
  We develop a fully automated pipeline and construct a large-scale dataset named MidEast-TE from about 0.6 million news articles. This dataset focuses on the cooperation and conflict events among countries mainly in the MidEast region from 2015 to 2022. We propose a novel method LoGo that is able to take advantage of both Local and Global contexts for SCTc-TE forecasting.
  arXiv  Detail & Related papers  (2023-12-02T07:40:21Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Performative Time-Series Forecasting [64.03865043422597]
  We formalize performative time-series forecasting (PeTS) from a machine-learning perspective.<n>We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts.<n>We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-09T18:34:29Z)
• Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network [0.8378605337114742]
  We propose a novel framework that encodes seasonal climate predictions to provide robust and reliable time-series forecasting for supply chain functions. Our experiments indicate learning such representations to model seasonal climate forecast results in an error reduction of approximately 13% to 17% across multiple real-world data sets.
  arXiv  Detail & Related papers  (2023-09-05T13:58:59Z)
• Self-Interpretable Time Series Prediction with Counterfactual Explanations [4.658166900129066]
  Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving. Most existing methods focus on interpreting predictions by assigning important scores to segments of time series. We develop a self-interpretable model, dubbed Counterfactual Time Series (CounTS), which generates counterfactual and actionable explanations for time series predictions.
  arXiv  Detail & Related papers  (2023-06-09T16:42:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.