{"total":25,"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":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"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":"2512.08868","title":"EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2512.05671","title":"ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education","created":"2025-12-05","cited_by_count":6,"area":null},{"id":"2603.20807","title":"BenchBench: Benchmarking Automated Benchmark Generation","created":"2026-03-21","cited_by_count":5,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","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":"2511.18394","title":"Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking","created":"2025-11-23","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":"2606.29661","title":"Diversity is the Strength of the AI Crowd","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2601.06088","title":"PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2603.03322","title":"Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.02378","title":"YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches","created":"2026-04-01","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":"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":"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":"2607.29503","title":"The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting","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":"2609.33257","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":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}