An open library for your next question. Public pilot
Executable Science
Log inCreate account
THE OPEN LIBRARY

Find your next starting point.

Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.

246 resources · Curated orderClear filters
Software

PyTorch

Upstream project repository

Tensor computation and automatic differentiation framework for constructing controlled learning and gradient experiments.

Investigate Do automatic gradients agree with analytical derivatives for a small well-conditioned scalar objective?

Listing reviewed · source terms apply
Software

PyTorch Lightning

Upstream project repository

Training-loop framework for studying checkpoint restoration, reproducibility and separation of model logic from orchestration.

Investigate Does resuming a tiny deterministic run from a checkpoint match its uninterrupted reference?

Listing reviewed · source terms apply
Datasets

QSAR aquatic toxicity

UCI Machine Learning Repository

Chemical descriptors and aquatic bioassay outcomes for a bounded ecotoxicology regression audit.

Investigate Which compounds dominate aquatic-toxicity error after train-only preprocessing and influence analysis?

Listing reviewed · source terms apply
Datasets

QSAR biodegradation

UCI Machine Learning Repository

Molecular descriptors and biodegradation labels for checking chemical prediction protocols.

Investigate How does chemical-group-aware splitting change biodegradation classification performance?

Listing reviewed · source terms apply
Datasets

QSAR fish bioconcentration factor (BCF)

UCI Machine Learning Repository

Chemical descriptors and fish bioconcentration factors for studying environmental-property prediction.

Investigate How does bioconcentration prediction change when related chemicals are kept in the same fold?

Listing reviewed · source terms apply
Datasets

QSAR fish toxicity

UCI Machine Learning Repository

Molecular descriptors and aquatic toxicity measurements for studying chemical regression uncertainty.

Investigate How does fish-toxicity prediction change under chemical-group-aware splitting?

Listing reviewed · source terms apply
Datasets

Raisin

UCI Machine Learning Repository

Raisin morphology measurements for an interpretable food-classification benchmark.

Investigate How stable is raisin-variety classification across fixed stratified splits and measurement normalization?

Listing reviewed · source terms apply
Software

Ray

Upstream project repository

Distributed execution and machine-learning infrastructure for studying task scheduling, tuning and fault handling.

Investigate Does a small synthetic parameter sweep retain each trial's identity and failure state under a declared retry policy?

Listing reviewed · source terms apply
Datasets

Rice (Cammeo and Osmancik)

UCI Machine Learning Repository

Rice-grain shape measurements for a compact agricultural classification study.

Investigate Which geometric features preserve rice-variety discrimination under a frozen evaluation protocol?

Listing reviewed · source terms apply
Datasets

Robot Execution Failures

UCI Machine Learning Repository

Robot-operation measurements and failure types for investigating grouped fault detection.

Investigate How does robot failure classification change when whole execution episodes are held out?

Listing reviewed · source terms apply
Software

Sacred

Upstream project repository

Experiment organization and observation tooling for capturing configurations, dependencies and run outcomes.

Investigate Does a controlled failed run preserve its configuration and failure outcome as clearly as a successful run?

Listing reviewed · source terms apply
Software

SciCode

Upstream project repository

Scientific coding benchmark repository linking problem formulations and evaluation logic for researcher-oriented model assessment.

Investigate Can one rights-reviewed scientific coding task distinguish a syntactically valid solution from numerical correctness under fixed tolerances?

Listing reviewed · source terms apply

Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.