Papers

Field

Top tools here

Open problems in Forecasting time

Event-driven forecasting with noisy and sparse signals1 paper raises it · 2 address it
Real-world time series are often influenced by exogenous events, but current methods struggle to retrieve, filter, and reason about these events causally.
- SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecastingraises · addresses
- TimeBraid: Unifying Time Series and Language for Understanding and Forecastingaddresses
Dependence structure in multivariate trajectory forecasting1 paper raises it · 1 addresses it
Most models predict marginal quantiles, ignoring the joint dependence of future paths, which is critical for downstream tasks like cumulative demand or peak load.
- PathFM: Fast Generative Forecasting of Multivariate Trajectoriesraises · addresses
Intervention-aware forecasting under covariate shifts1 paper raises it · 1 addresses it
Models must reliably forecast responses to future events that set covariates to unseen values, but current benchmarks and methods fall short.
- WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecastingraises · addresses
Evaluation bias from wet-biased data pipelines1 paper raises it · 1 addresses it
Generative models for precipitation nowcasting are misled by target-dependent sampling, which distorts calibration assessment and model development.
- Wet-Biased Data Pipelines Mislead the Training and Evaluation of Generative Precipitation Nowcastingraises · addresses
Individual-level fidelity in agentic forecasting1 paper raises it · 0 address it
LLMs used as user simulators often fail to reproduce fine-grained decision logic and portfolio trajectories, despite coarse behavioral agreement.
- Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulationraises

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

forecasting time · forecasters · forecasting189 papers28 this week
weather forecasting · weather prediction · forecasts155 papers23 this week
financial forecasting · based trading · price forecasting72 papers18 this week
data assimilation · forecast · probabilistic forecasting61 papers7 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.AIOct 19
Beyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation Models
Hongyin Zhang, Mingyi Xiang, Rongzhao Chen, Yankai Wang, Jialin Qiao +5
Static public benchmarks for time series foundation models (TSFMs) typically have fixed and narrow test distributions. Their repeated reuse encourages benchmark-specific tuning, making reported performance reflect adaptation to the fixed test set rather than genuine forecasting generalization. In addition, a single aggregate score cannot fully characterize model capabilities across distinct temporal structures and input relationships. We propose CaFE (Capability-Focused Evaluation), a refreshable evaluation extension grounded in original benchmark data that enriches static benchmarks with structural diversity and enriches single-score black-box evaluation with multi-dimensional, capability-oriented assessment. CaFE first profiles the original benchmark and defines eight Structural Features (SFs) that characterize its temporal structure. For each SF, it resamples the original data according to its structural support, removes edge-of-distribution samples, and augments the retained samples by varying the SF's salience, producing samples with different structural profiles. After filtering out out-of-distribution samples while preserving diversity, CaFE yields a refreshed evaluation…
PDF arXiv
arXiv cs.LGOct 19
OceanTensorCube and ST-MMT: A Multimodal Data and Transformer System for Seven-Day Forecasting of Pyropia Bleaching
Gwangjin Kim, Cheolyoung Jang, Yosep Jo
Bleaching of cultured Pyropia (laver) causes losses in Korean seaweed farming. We present a system that forecasts bleaching seven days ahead for farm clusters. OceanTensorCube aligns 32 channels from public marine, meteorological, ocean-model and satellite sources on a 30 m grid, and ST-MMT, a 9.2-million-parameter spatiotemporal transformer with hub-style multi-head cross-attention between variable groups, maps a 14-day input window to a seven-day-ahead bleaching probability. On the validation set, a six-seed ensemble detects every reported positive at a false-alarm rate of at most 3.5%, an upper bound because the report-based labels are positive-unlabeled. A same-date control on separately trained models indicates that the architecture discriminates between clusters when the calendar is held fixed. We also report the system's weaknesses: skill falls steeply as the quarterly nutrient survey ages (ROC-AUC 0.94 at 30 days, 0.53 at 129 days), and a single LSTM on cluster-average series outperforms a single ST-MMT, with only the ensemble leading at the operating point. We describe the labeling procedure, the evaluation protocol and the operational gate that withholds forecasts when…
PDF arXiv
arXiv cs.LGOct 19
FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation
Yuxuan Wu, Miaopei Lin, Qiufang Ying, Lin Dan, Hao Zhao +7
Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial way: each intermediate answer is an exact typed constraint, such as an entity, date, event, or numerical indicator, that determines the next query. This strict answer-conditioned dependency makes small intermediate errors cascade into plausible but wrong search trajectories. We introduce FinHopper, a benchmark for complex financial agents with controlled reasoning depth from 1 to 6 hops, covering stocks, funds, and macroeconomic facts, with gold intermediate answers for process-level evaluation. To construct FinHopper at scale, we design a state-transition-based synthesis framework that composes verified atomic financial QA patterns into dependency-preserving chains, followed by targeted in-synthesis verification, model-ensemble checking, and public-search validation by financial experts. Experiments with 20 LLM-agent configurations show that public search tools are necessary but insufficient: performance drops sharply as hop depth increases, the best model remains far below human experts, and process-aware…
PDF arXiv
arXiv cs.AIOct 19
TimesJev: Thinking Fast on Time Series with System 1 Sufficiency
Chenghao Liu, Wei Fan, Jindong Han, Dongjie Wang, Aniket Mahanti +2
Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thought. However, this process often consumes thousands of tokens, directly leading to substantial latency during inference. In contrast, System 1 models such as Jev make decisions instantly and can naturally be an alternative, but raw time series are not compatible with the embedding space of these models, thus hindering the reasoning performance, especially when input series contain thousands of numeric points. In this paper, we make a very early attempt to propose a time series System 1 model, namely TimesJev. Specifically, we first formalize System 1 sufficiency in time series reasoning, which motivates a compressed representation for time series with key frequency patterns preserved. To construct this representation, we derive a dimension reduction objective that combines (i) a sufficiency divergence that measures the core information lost during compression, and (ii) a realizability divergence that quantifies the incompatibility of the System 1 model to the optimal prediction given this representation. We…
PDF arXiv
arXiv cs.AIOct 19
Global probabilistic forecasting of air pollution
Ammar Kheder, Michael Boy, Zhi-song Liu
Fine particulate matter (PM2.5) refers to particulate matter with an aerodynamic diameter of 2.5 micrometre or less. It comes from human activities, such as traffic and industry, and from wildfires, desert dust and gases emitted by vegetation. Short-term exposure to it accounts for about a million deaths a year. Operational forecasts run on grids tens of kilometres wide, which hide the pollution breathed by nearly two hundred million people a day. Machine learning has transformed weather forecasting, but data-driven forecasts of air pollution still blur extremes and lose skill as the air travels. Here we introduce Foehn, a generative model that learns from global kilometre-scale estimates of PM2.5 and computes where the air comes from. Over a year of retrospective forecasts, it outperforms the operational forecast at three stations in four and forecasts at the scale of this hidden exposure. Its ensembles are calibrated, and their mean detects local pollution extremes four days ahead as well as the operational forecast does one day ahead. Such forecasts could warn the millions whom coarse maps miss, once kilometre-scale data are available in real time.
PDF arXiv
arXiv cs.CLOct 19
LEAPS: Long-context Evaluation of Adaptive Pattern Learning and State Tracking
Howard Yen, Nitya Mani, Alex Renda, Christopher S. Hardin
Long-context language models (LCLMs) power agents that act over long trajectories, from improving a codebase to running research experiments to forecasters that condition on lengthy histories. These applications draw on three distinct long-context capabilities: recall, where the answer is a fact present in the context; state tracking, where the outcome can be computed by performing a series of transformations to a specified state; and pattern learning, where the goal is to make a prediction by sampling from a distribution inferred from many observations. Existing benchmarks primarily focus on the first capability. In this work, we introduce LEAPS (Long-context Evaluation of Adaptive Pattern learning and State tracking), a collection of 12 novel datasets, spanning agentic workflows, behavioral modeling, and forecasting of market and world events. By construction, LEAPS is resistant to data contamination, extends to millions of input tokens, and uses reliable metrics. We evaluate 30 API and open models from 8K to 512K input tokens. LEAPS distinguishes models that perform near perfectly on recall tasks, finding that such models' state tracking and pattern learning abilities can vary…
PDF arXiv

Papers

Topics in this field

forecasting time · forecasters · forecasting189 papers28 this week
weather forecasting · weather prediction · forecasts155 papers23 this week
financial forecasting · based trading · price forecasting72 papers18 this week
data assimilation · forecast · probabilistic forecasting61 papers7 this week

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

Recent papers

All in Research →

arXiv cs.AIOct 19
Beyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation Models
Hongyin Zhang, Mingyi Xiang, Rongzhao Chen, Yankai Wang, Jialin Qiao +5
Static public benchmarks for time series foundation models (TSFMs) typically have fixed and narrow test distributions. Their repeated reuse encourages benchmark-specific tuning, making reported performance reflect adaptation to the fixed test set rather than genuine forecasting generalization. In addition, a single aggregate score cannot fully characterize model capabilities across distinct temporal structures and input relationships. We propose CaFE (Capability-Focused Evaluation), a refreshable evaluation extension grounded in original benchmark data that enriches static benchmarks with structural diversity and enriches single-score black-box evaluation with multi-dimensional, capability-oriented assessment. CaFE first profiles the original benchmark and defines eight Structural Features (SFs) that characterize its temporal structure. For each SF, it resamples the original data according to its structural support, removes edge-of-distribution samples, and augments the retained samples by varying the SF's salience, producing samples with different structural profiles. After filtering out out-of-distribution samples while preserving diversity, CaFE yields a refreshed evaluation…
PDF arXiv
arXiv cs.LGOct 19
OceanTensorCube and ST-MMT: A Multimodal Data and Transformer System for Seven-Day Forecasting of Pyropia Bleaching
Gwangjin Kim, Cheolyoung Jang, Yosep Jo
Bleaching of cultured Pyropia (laver) causes losses in Korean seaweed farming. We present a system that forecasts bleaching seven days ahead for farm clusters. OceanTensorCube aligns 32 channels from public marine, meteorological, ocean-model and satellite sources on a 30 m grid, and ST-MMT, a 9.2-million-parameter spatiotemporal transformer with hub-style multi-head cross-attention between variable groups, maps a 14-day input window to a seven-day-ahead bleaching probability. On the validation set, a six-seed ensemble detects every reported positive at a false-alarm rate of at most 3.5%, an upper bound because the report-based labels are positive-unlabeled. A same-date control on separately trained models indicates that the architecture discriminates between clusters when the calendar is held fixed. We also report the system's weaknesses: skill falls steeply as the quarterly nutrient survey ages (ROC-AUC 0.94 at 30 days, 0.53 at 129 days), and a single LSTM on cluster-average series outperforms a single ST-MMT, with only the ensemble leading at the operating point. We describe the labeling procedure, the evaluation protocol and the operational gate that withholds forecasts when…
PDF arXiv
arXiv cs.LGOct 19
FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation
Yuxuan Wu, Miaopei Lin, Qiufang Ying, Lin Dan, Hao Zhao +7
Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial way: each intermediate answer is an exact typed constraint, such as an entity, date, event, or numerical indicator, that determines the next query. This strict answer-conditioned dependency makes small intermediate errors cascade into plausible but wrong search trajectories. We introduce FinHopper, a benchmark for complex financial agents with controlled reasoning depth from 1 to 6 hops, covering stocks, funds, and macroeconomic facts, with gold intermediate answers for process-level evaluation. To construct FinHopper at scale, we design a state-transition-based synthesis framework that composes verified atomic financial QA patterns into dependency-preserving chains, followed by targeted in-synthesis verification, model-ensemble checking, and public-search validation by financial experts. Experiments with 20 LLM-agent configurations show that public search tools are necessary but insufficient: performance drops sharply as hop depth increases, the best model remains far below human experts, and process-aware…
PDF arXiv
arXiv cs.AIOct 19
TimesJev: Thinking Fast on Time Series with System 1 Sufficiency
Chenghao Liu, Wei Fan, Jindong Han, Dongjie Wang, Aniket Mahanti +2
Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thought. However, this process often consumes thousands of tokens, directly leading to substantial latency during inference. In contrast, System 1 models such as Jev make decisions instantly and can naturally be an alternative, but raw time series are not compatible with the embedding space of these models, thus hindering the reasoning performance, especially when input series contain thousands of numeric points. In this paper, we make a very early attempt to propose a time series System 1 model, namely TimesJev. Specifically, we first formalize System 1 sufficiency in time series reasoning, which motivates a compressed representation for time series with key frequency patterns preserved. To construct this representation, we derive a dimension reduction objective that combines (i) a sufficiency divergence that measures the core information lost during compression, and (ii) a realizability divergence that quantifies the incompatibility of the System 1 model to the optimal prediction given this representation. We…
PDF arXiv
arXiv cs.AIOct 19
Global probabilistic forecasting of air pollution
Ammar Kheder, Michael Boy, Zhi-song Liu
Fine particulate matter (PM2.5) refers to particulate matter with an aerodynamic diameter of 2.5 micrometre or less. It comes from human activities, such as traffic and industry, and from wildfires, desert dust and gases emitted by vegetation. Short-term exposure to it accounts for about a million deaths a year. Operational forecasts run on grids tens of kilometres wide, which hide the pollution breathed by nearly two hundred million people a day. Machine learning has transformed weather forecasting, but data-driven forecasts of air pollution still blur extremes and lose skill as the air travels. Here we introduce Foehn, a generative model that learns from global kilometre-scale estimates of PM2.5 and computes where the air comes from. Over a year of retrospective forecasts, it outperforms the operational forecast at three stations in four and forecasts at the scale of this hidden exposure. Its ensembles are calibrated, and their mean detects local pollution extremes four days ahead as well as the operational forecast does one day ahead. Such forecasts could warn the millions whom coarse maps miss, once kilometre-scale data are available in real time.
PDF arXiv
arXiv cs.CLOct 19
LEAPS: Long-context Evaluation of Adaptive Pattern Learning and State Tracking
Howard Yen, Nitya Mani, Alex Renda, Christopher S. Hardin
Long-context language models (LCLMs) power agents that act over long trajectories, from improving a codebase to running research experiments to forecasters that condition on lengthy histories. These applications draw on three distinct long-context capabilities: recall, where the answer is a fact present in the context; state tracking, where the outcome can be computed by performing a series of transformations to a specified state; and pattern learning, where the goal is to make a prediction by sampling from a distribution inferred from many observations. Existing benchmarks primarily focus on the first capability. In this work, we introduce LEAPS (Long-context Evaluation of Adaptive Pattern learning and State tracking), a collection of 12 novel datasets, spanning agentic workflows, behavioral modeling, and forecasting of market and world events. By construction, LEAPS is resistant to data contamination, extends to millions of input tokens, and uses reliable metrics. We evaluate 30 API and open models from 8K to 512K input tokens. LEAPS distinguishes models that perform near perfectly on recall tasks, finding that such models' state tracking and pattern learning abilities can vary…
PDF arXiv

Open problems in Forecasting time

Event-driven forecasting with noisy and sparse signals1 paper raises it · 2 address it
Real-world time series are often influenced by exogenous events, but current methods struggle to retrieve, filter, and reason about these events causally.
- SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecastingraises · addresses
- TimeBraid: Unifying Time Series and Language for Understanding and Forecastingaddresses
Dependence structure in multivariate trajectory forecasting1 paper raises it · 1 addresses it
Most models predict marginal quantiles, ignoring the joint dependence of future paths, which is critical for downstream tasks like cumulative demand or peak load.
- PathFM: Fast Generative Forecasting of Multivariate Trajectoriesraises · addresses
Intervention-aware forecasting under covariate shifts1 paper raises it · 1 addresses it
Models must reliably forecast responses to future events that set covariates to unseen values, but current benchmarks and methods fall short.
- WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecastingraises · addresses
Evaluation bias from wet-biased data pipelines1 paper raises it · 1 addresses it
Generative models for precipitation nowcasting are misled by target-dependent sampling, which distorts calibration assessment and model development.
- Wet-Biased Data Pipelines Mislead the Training and Evaluation of Generative Precipitation Nowcastingraises · addresses
Individual-level fidelity in agentic forecasting1 paper raises it · 0 address it
LLMs used as user simulators often fail to reproduce fine-grained decision logic and portfolio trajectories, despite coarse behavioral agreement.
- Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulationraises

Named by an AI from these papers' abstracts.

Fields · AI · updated 54m ago

Forecasting time

Found by the topic model: forecasting time, weather forecasting, financial forecasting.

76papers this week−16.5% vs last week

All papers · 477 With code · 3

Newest Most relevant

449 papers this month