mlsanityData to 7 Oct 2026

Benchmarking Simulacra AI's Quantum Accurate Synthetic Data Generation for Chemical Sciences

arXiv 2511.07433 ↗First posted 30 Oct 2025physics.chem-ph cs.AI physics.comp-phcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work, we benchmark simulacra's synthetic data generation pipeline against a state-of-the-art Microsoft pipeline on a dataset of small to large systems. By analyzing the energy quality, autocorrelation times, and effective sample size, our findings show that Simulacra's Large Wavefunction Models (LWM) pipeline, paired with state-of-the-art Variational Monte Carlo (VMC) sampling algorithms, reduces data generation costs by 15-50x, while maintaining parity in energy accuracy, and 2-3x compared to traditional CCSD methods on the scale of amino acids. This enables the creation of affordable, large-scale textitab-initio datasets, accelerating AI-driven optimization and discovery in the pharmaceutical industry and beyond. Our improvements are based on a novel and proprietary sampling scheme called Replica Exchange with Langevin Adaptive eXploration (RELAX).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 76 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

20 of 76 references.

References · 20

  1. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  2. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  3. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  4. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
  5. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 242
  6. 2019Ab-Initio Solution of the Many-Electron Schr"odinger Equation with Deep Neural Networkscited by 195
  7. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 80
  8. 2022A Self-Attention Ansatz for Ab-initio Quantum Chemistrycited by 45
  9. 2021Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functionscited by 36
  10. 2023Generalizing Neural Wave Functionscited by 26
  11. 2021Local-Global MCMC kernels: the best of both worldscited by 21
  12. 2023Accurate Computation of Quantum Excited States with Neural Networkscited by 16
8 more
  1. 2024A Survey on Universal Approximation Theoremscited by 15
  2. 2023Neural Wave Functions for Superfluidscited by 12
  3. 2025An ab initio foundation model of wavefunctions that accurately describes chemical bond breakingcited by 11
  4. 2021Analysis of autocorrelation times in Neural Markov Chain Monte Carlo simulationscited by 10
  5. 2023Variational Monte Carlo on a Budget -- Fine-tuning pre-trained Neural Wavefunctionscited by 8
  6. 2024Neural Pfaffians: Solving Many Many-Electron Schr"odinger Equationscited by 8
  7. 2025Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problemscited by 8
  8. 2024Transferable Neural Wavefunctions for Solidscited by 7

Built on by

Not cited yet.