Cover Image

Simulation as Supervision: Mechanistic Pretraining for Scientific Discovery

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dudley, Carson, Magdaleno, Reiden, Harding, Christopher, Eisenberg, Marisa
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mantis: A Foundation Model for Mechanistic Disease Forecasting
by: Dudley, Carson, et al.
Published: (2025)

Learning From Simulators: A Theory of Simulation-Grounded Learning
by: Dudley, Carson, et al.
Published: (2025)

Prediction Markets Underperform Simple Baselines For Infectious Disease Forecasting
by: Dudley, Carson, et al.
Published: (2026)

In-Context Learning Under Regime Change
by: Dudley, Carson, et al.
Published: (2026)

Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems
by: Kramer, Stefan, et al.
Published: (2023)

Evaluation-driven Scaling for Scientific Discovery
by: Ye, Haotian, et al.
Published: (2026)

Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
by: Liao, Ning, et al.
Published: (2025)

The Use of AI-Robotic Systems for Scientific Discovery
by: Gower, Alexander H., et al.
Published: (2024)

Artificial Scientific Discovery
by: Norelli, Antonio
Published: (2024)

Post-hoc Interpretability Illumination for Scientific Interaction Discovery
by: Zhang, Ling, et al.
Published: (2024)

Principle-Evolvable Scientific Discovery via Uncertainty Minimization
by: Pu, Yingming, et al.
Published: (2026)

Supervised Pretraining for Material Property Prediction
by: Rahman, Chowdhury Mohammad Abid, et al.
Published: (2025)

These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining
by: Yang, Xingyu Alice, et al.
Published: (2025)

Mechanistic Neural Networks for Scientific Machine Learning
by: Pervez, Adeel, et al.
Published: (2024)

Nature Language Model: Deciphering the Language of Nature for Scientific Discovery
by: Xia, Yingce, et al.
Published: (2025)

Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges
by: Reddy, Chandan K, et al.
Published: (2024)

Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention
by: Sandoval, Gustavo
Published: (2025)

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
by: Ariguib, Boshra, et al.
Published: (2025)

PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration
by: Pu, Yingming, et al.
Published: (2025)

Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery
by: Yang, Robert
Published: (2025)

DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
by: Jiang, Jiachen, et al.
Published: (2026)

Prior-Guided Symbolic Regression: Towards Scientific Consistency in Equation Discovery
by: Xiao, Jing, et al.
Published: (2026)

Adaptive Spatio-Temporal Graphs with Self-Supervised Pretraining for Multi-Horizon Weather Forecasting
by: Liu, Yao
Published: (2025)

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
by: Agarwal, Dhruv, et al.
Published: (2025)

Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
by: Levy, Jacob, et al.
Published: (2026)

AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing
by: Bright-Thonney, Samuel, et al.
Published: (2025)

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
by: Muhammad, Hada Melino, et al.
Published: (2026)

Reduction of Supervision for Biomedical Knowledge Discovery
by: Theodoropoulos, Christos, et al.
Published: (2025)

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
by: Ma, Pingchuan, et al.
Published: (2024)

CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
by: Mroueh, Youssef, et al.
Published: (2026)

MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
by: Fan, Shicheng, et al.
Published: (2026)

LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization
by: Wang, Boxiao, et al.
Published: (2026)

LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
by: Kabra, Sanchit, et al.
Published: (2026)

BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization
by: Zakarias, Gustav Wagner, et al.
Published: (2024)

Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
by: Saveliev, Evgeny S., et al.
Published: (2026)

On Pretraining Data Diversity for Self-Supervised Learning
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

The Need for a Big World Simulator: A Scientific Challenge for Continual Learning
by: Kumar, Saurabh, et al.
Published: (2024)

Martingale-Consistent Self-Supervised Learning
by: Gögl, Moritz, et al.
Published: (2026)

Deep Learning Opacity in Scientific Discovery
by: Duede, Eamon
Published: (2022)

Weakly Supervised Pretraining and Multi-Annotator Supervised Finetuning for Facial Wrinkle Detection
by: Moon, Ik Jun, et al.
Published: (2024)