# Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data

arXiv: https://arxiv.org/abs/2607.19816 · HTML: https://mlsanity.com/paper/2607.19816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 44 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 3 of 3)

- [Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry](https://mlsanity.com/paper/2407.17492/) (2024)
- [Accurate and efficient structure elucidation from routine one-dimensional NMR spectra using multitask machine learning](https://mlsanity.com/paper/2408.08284/) (2024)
- [A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement](https://mlsanity.com/paper/2601.22723/) (2026)

## Abstract (arXiv)

Determining molecular structures from spectroscopic data remains fundamentally challenging because the inverse problem is intrinsically underdetermined: individual spectra are sparse, low-dimensional, and encode only partial structural evidence relative to the vast space of possible molecules. We address this challenge by formulating automated structure elucidation as a scalable hypothesis-refinement paradigm that tightly integrates spectral evidence with large-scale molecular priors. To supply structure-resolving NMR signals for multimodal learning, we construct QM9SPIN, a DFT-derived dataset comprising diverse 1D and 2D spectra, including J-coupling, DEPT experiments, and explicit spin--spin interactions. On this foundation, we introduce SpectroMol, a spectrum-to-structure model that proposes chemically valid molecular hypotheses conditioned on multimodal spectral inputs. Complementarily, we develop MS-Mol2Mol, a high-resolution mass-constrained molecular generator that integrates molecular formula, exact mass, and degree of unsaturation within a conditional generative prior trained on 400 million molecules, ensuring global compositional consistency and chemically realistic refinement. The integrated system achieves 93.8% top-1 accuracy on the simulated benchmark, adapts effectively from simulated to experimental spectra with limited experimental fine-tuning, and further improves experimental predictions through mass-guided refinement, establishing a scalable route toward automated, data-driven organic structure elucidation.