·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
America needs to stop getting shocked by Chinese AI1h◆Advancing next-gen AI with materials science innovation1h◆Gritt exits stealth with $34 million for robots to build solar plants—then, everything else2h◆Capacity and Redundancy Trade-offs in Multi-Task Learning8h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation8h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making8h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection8h◆Supervised Reward Inference8h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization8h◆Is Progressive Disclosure All You Need for Long-Context Agents?8h◆Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer8h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability8h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification8h◆Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent8h◆RealDESED: A Real-World Domestic Sound Event Detection Benchmark8h◆Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones8h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration8h◆Autonomous Discovery of Wireless Communications Algorithms8h◆OrderMoE: An expert similarity driven distributed edge MoE inference8h◆Time-Frequency Consistency Learning for Robust Speech Deepfake Detection8h◆America needs to stop getting shocked by Chinese AI1h◆Advancing next-gen AI with materials science innovation1h◆Gritt exits stealth with $34 million for robots to build solar plants—then, everything else2h◆Capacity and Redundancy Trade-offs in Multi-Task Learning8h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation8h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making8h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection8h◆Supervised Reward Inference8h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization8h◆Is Progressive Disclosure All You Need for Long-Context Agents?8h◆Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer8h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability8h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification8h◆Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent8h◆RealDESED: A Real-World Domestic Sound Event Detection Benchmark8h◆Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones8h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration8h◆Autonomous Discovery of Wireless Communications Algorithms8h◆OrderMoE: An expert similarity driven distributed edge MoE inference8h◆Time-Frequency Consistency Learning for Robust Speech Deepfake Detection8h◆
News/FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches
arxiv
PublishedJuly 21, 2026 at 4:00 AM

FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches

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

arXiv:2607.17765v1 Announce Type: cross Abstract: We introduce WC2026-Agents, a benchmark and dataset for evaluating large language models (LLMs) as autonomous forecasting agents on real, future events. For every one of the 104 matches of the 2026 FIFA World Cup, four frontier models -- Claude Opus

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

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

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivCapacity and Redundancy Trade-offs in Multi-Task Learning8harxivPredictive Training with Latent Imagination for Visual Quadruped Navigation8harxivWhere Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making8harxivDid We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection8h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

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

Originally published on arxiv ↗
HomeModelsNews