Research map / Probabilistic and scientific modeling / Molecules and proteins
Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction
Yingheng Wang, Tao Yu, Shufeng Kong, Francesco Ricci, John M Gregoire, Carla P Gomes
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add constraint-preserving physical reasoning (mass-conserving refinement) (ablation) | DeepSciReasoner · eDOS CalTech | MSE: 20.990 -> 19.612 | Improved |
| add constraint-preserving physical reasoning (ablation) | DeepSciReasoner · eDOS TRI | MSE: 29.387 -> 27.162 | Improved |
| add structure-aware spectrum decoding on top of DSR-NR (ablation) | DeepSciReasoner · eDOS CalTech | MSE: 24.726 -> 20.990 | Improved |
| add structure-aware spectrum decoding on top of DSR-NR (ablation) | DeepSciReasoner · eDOS TRI | WD: 0.372 -> 0.329 | Improved |
| use DeepSciReasoner instead of strongest baseline | eDOS · eDOS CalTech | MSE: 24.675 -> 19.612 | Improved |
| use DeepSciReasoner instead of DOSTransformer | eDOS · eDOS TRI | R2: 0.716 -> 0.761 | Improved |
| apply DeepSciReasoner to XANES-full | spectrum prediction · XANES-full | R2: 0.657 -> 0.764 | Improved |
| apply DeepSciReasoner to Raman | spectrum prediction · Raman | R2: 0.115 -> 0.264 | Improved |
| apply DeepSciReasoner to phDOS | spectrum prediction · phDOS | MSE: 0.023 -> 0.021 | Improved |
| use DeepSciReasoner for VB-gap identification | eDOS · VB-gap TRI | F1: 0.509 -> 0.648 | Improved |
| increase training data from 25% to 75% | DeepSciReasoner · eDOS CalTech | R2, MAE, MSE, WD | Improved |
Closest papers by meaning
- Learning the Electronic Hamiltonian of Large Atomic Structures (ICML 2025 · similarity 0.84)
- A Denoising Pre-training Framework for Accelerating Novel Material Discovery (AAAI 2025 · similarity 0.84)
- A Diffusion-Based Pre-training Framework for Crystal Property Prediction (AAAI 2024 · similarity 0.83)
- MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra (ICLR 2025 · similarity 0.82)
- Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding (ICLR 2024 · similarity 0.82)
- All that structure matches does not glitter (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
