Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
- AI Research Preference Models
- Language Models (Mostly) Know What They Know
- Measuring Faithfulness in Chain-of-Thought Reasoning
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
- Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements
- Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
- AI scientists produce results without reasoning scientifically
- Scientific reasoning does not reliably translate into scientific forecasting in frontier AI
- EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems