·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation27m◆Counterfactual Model Testing Under Distribution Shift27m◆Centralized Critics for N-Agent Ad Hoc Teamwork27m◆Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning27m◆Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction27m◆Numina Fuse: Interactive Autoformalization in Lean 427m◆On the Limits of Sparse Linear Model with Shuffled Differential Privacy27m◆Video World Models Need Predictable Latents27m◆AutoPRL: Automated Path Representation Learning via a Learnable View Generator27m◆Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models27m◆Latent Goal Prediction from Language for Model-Based Planning27m◆Rectified Language Flow27m◆Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment27m◆Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila27m◆Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights27m◆Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training27m◆Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks27m◆DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training27m◆Unbiased Alignment for Large Language Models with Noisy Preferences27m◆ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration27m◆MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation27m◆Counterfactual Model Testing Under Distribution Shift27m◆Centralized Critics for N-Agent Ad Hoc Teamwork27m◆Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning27m◆Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction27m◆Numina Fuse: Interactive Autoformalization in Lean 427m◆On the Limits of Sparse Linear Model with Shuffled Differential Privacy27m◆Video World Models Need Predictable Latents27m◆AutoPRL: Automated Path Representation Learning via a Learnable View Generator27m◆Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models27m◆Latent Goal Prediction from Language for Model-Based Planning27m◆Rectified Language Flow27m◆Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment27m◆Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila27m◆Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights27m◆Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training27m◆Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks27m◆DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training27m◆Unbiased Alignment for Large Language Models with Noisy Preferences27m◆ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration27m◆
News/TimeSeek: Temporal Reliability of Agentic Forecasters
arxiv
PublishedApril 7, 2026 at 4:00 AM
—neutral

TimeSeek: Temporal Reliability of Agentic Forecasters

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.04220v1 Announce Type: new Abstract: We introduce TimeSeek, a benchmark for studying how the reliability of agentic LLM forecasters changes over a prediction market's lifecycle. We evaluate 10 frontier models on 150 CFTC-regulated Kalshi binary markets at five temporal checkpoints, with a

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Mentioned models
01
  • 01
    TimeSeek
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#benchmark#forecasting#evaluation#llm
Mentioned companies
02
KalshiCFTC

No replies yet. Be first.

Mentioned models
01
  • 01
    TimeSeek
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#benchmark#forecasting#evaluation#llm
Mentioned companies
02
KalshiCFTC

Related coverage

More from ARXIV
arxivMAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation27marxivCounterfactual Model Testing Under Distribution Shift27marxivCentralized Critics for N-Agent Ad Hoc Teamwork27marxivWhere and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning27m
The Bubble Brief
MON · WED · FRI

Read benchmark insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews