{"total":70,"rows":[{"id":"2510.17638","title":"LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena","created":"2025-10-20","cited_by_count":40,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2506.00723","title":"Pitfalls in Evaluating Language Model Forecasters","created":"2025-05-31","cited_by_count":23,"area":null},{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2506.00794","title":"Predicting Empirical AI Research Outcomes with Language Models","created":"2025-06-01","cited_by_count":17,"area":null},{"id":"2604.14199","title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","created":"2026-04-03","cited_by_count":12,"area":null},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2503.14190","title":"Inferring Events from Time Series using Language Models","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2511.07678","title":"AIA Forecaster: Technical Report","created":"2025-11-10","cited_by_count":9,"area":null},{"id":"2603.03992","title":"Measuring AI R&D Automation","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2502.19676","title":"FOReCAst: The Future Outcome Reasoning and Confidence Assessment Benchmark","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2504.01509","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2507.04562","title":"Evaluating LLMs on Real-World Forecasting Against Expert Forecasters","created":"2025-07-06","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2507.19477","title":"Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2601.13717","title":"Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff","created":"2026-01-20","cited_by_count":6,"area":null},{"id":"2512.16030","title":"Do Large Language Models Know What They Don't Know? Kalshibench: A New Benchmark for Evaluating Epistemic Calibration via Prediction Markets","created":"2025-12-17","cited_by_count":5,"area":null},{"id":"2603.08707","title":"Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting","created":"2026-03-09","cited_by_count":4,"area":null},{"id":"2605.00420","title":"Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2601.22444","title":"Automating Forecasting Question Generation and Resolution for AI Evaluation","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2604.27865","title":"KellyBench: A Benchmark for Long-Horizon Sequential Decision Making","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2609.02797","title":"Dutch Books for Language Models","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2509.20645","title":"Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2509.23936","title":"Do Language Models Update their Forecasts with New Information?","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2511.21570","title":"From Prediction to Foresight: The Role of AI in Designing Responsible Futures","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2602.17234","title":"All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2604.16742","title":"CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2605.03762","title":"OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.16358","title":"LEAF: A Living Benchmark for Event-Augmented Forecasting","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.21491","title":"Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2605.27904","title":"Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.18686","title":"ForecastBench-Sim: A Simulated-World Forecasting Benchmark","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2606.29661","title":"Diversity is the Strength of the AI Crowd","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.00164","title":"Verifiable Rewards for Calibrated Probabilistic Forecasting","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2608.02985","title":"Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2609.00747","title":"Can Large Language Models Forecast What Researchers Study Next?","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2604.15719","title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.24705","title":"Energy-Arena: A Dynamic Benchmark for Operational Energy Forecasting","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2604.26106","title":"Evaluating Strategic Reasoning in Forecasting Agents","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2607.14051","title":"Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.24573","title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2607.24780","title":"LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2608.04009","title":"SocietyBench: Forecasting Counterfactual Social-World Evolution","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.20920","title":"ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.30110","title":"Can LLMs Take the Pulse of the Economy? A Real-Time Evaluation of LLM Nowcasts on Macroeconomic Indicators","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.01337","title":"LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2602.00758","title":"Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.16642","title":"When AI Navigates the Fog of War","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.15859","title":"QuantSightBench: Evaluating LLM Quantitative Forecasting with Prediction Intervals","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.22672","title":"Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.26074","title":"StakeBench: Evaluating Language Understanding Grounded in Market Commitment","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.24996","title":"From Forecasting Leaderboards to Deployment Decisions: A Fail-Closed Certification Protocol","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.03015","title":"Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.04389","title":"Decentralized Aggregation of LLM Predictions via Wagering Mechanisms","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.06656","title":"Robust Human-AI Complementarity under Uncertainty","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.09921","title":"Global Merger-Arbitrage Forecasting with Language Models","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.03569","title":"Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.04008","title":"WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.15798","title":"Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.28482","title":"How Proper Scoring Rules Shape LLM Forecasting","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.06117","title":"STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.12101","title":"When Do Language Models Add Value? Relative Competence in Hybrid Event Forecasting","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.16189","title":"Position: AI Is Not Ready for Strategic Conflicts","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.22246","title":"The Corroboration Illusion: When More News Makes LLM Forecasts Less True","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.32885","title":"Can LLMs Predict the Future? A Brier Score Analysis of Prediction Markets","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33257","title":"Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35879","title":"CruxBench: A Benchmark of Information Discovery","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.04888","title":"No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}