Skip to content

Company

Nature Computational Science

Peer-reviewed Nature Portfolio journal publishing research and commentary on computational methods, AI, and data-driven science.

Known aliases

  • Nat Comput Sci
  • Nat. Comput. Sci.

Current stories

scienceOne report1 publisher

Language models stay blind to atomic geometry even at 70 billion parameters, a materials study finds

LLMs fail to learn from atomic coordinates at up to 70 billion parameters and 2 million structures, a paper on nature.com reports. Specialized geometric architectures still win when structure dominates the property, the authors report.

Publishers:nature.com

Reality

Evidence66
Adoption
Not scored
Hype gap−5
Incentives
Not scored
Confidence60
scienceOne report1 publisher

Hessian Interatomic Potentials skip autodiff and finite differences to predict molecular Hessians

Hessian Interatomic Potentials predict molecular Hessians directly and run one to two orders of magnitude faster, their authors report. A cheaper Hessian would make second-order chemistry workflows easier to run routinely, if the reported gains survive independent tests.

Publishers:nature.com

Reality

Evidence45
Adoption
Not scored
Hype gap+15
Incentives
Not scored
Confidence55
scienceOne report1 publisher

A Nature analysis sorts LLM human proxies into four roles that each need their own validity test

The analysis argues that a model standing in for people can be sound for one research purpose and unsound for the next, and that the four purposes it identifies each rest on a different claim about human likeness.

Publishers:nature.com

Reality

Evidence52
Adoption
Not scored
Hype gap+6
Incentives40
Confidence54
scienceOne report1 publisher

MutexaGPT translates a chemist's plain-English hunch into a configured physics workflow

Its agents interview the user for what the request leaves out, then build and run the modelling. The paper shows this on two enzymes, which demonstrates the pipeline rather than measuring how often it is right.

Publishers:nature.com

Reality

Evidence48
Adoption
Not scored
Hype gap+30
Incentives65
Confidence52
scienceOne report1 publisher

PathSegmentor swaps the click for a typed description in pathology segmentation

Chen and colleagues report that a single text-prompted model scored highest overall across 16 pathology test sets, measured against baselines their code list names. The abstract publishes the counts; the margins are left out.

Publishers:nature.com

Reality

Evidence45
Adoption15
Hype gap+30
Incentives55
Confidence55
scienceOne report1 publisher

PULSE infers proteins and metabolites from routine bloods, then predicts six diseases at 0.72-0.83

The UK Biobank study reports generated metabolomic profiles beating every benchmark, and disease models built on synthetic proteomics at AUC 0.72 to 0.83. The check exists only where the assays were run.

Publishers:nature.com

Reality

Evidence58
Adoption
Not scored
Hype gap+18
Incentives38
Confidence55