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

Triton

Upstream project repository

GPU programming language and compiler for developing inspectable tensor kernels and testing numerical/performance tradeoffs.

Investigate Does a tiled matrix-multiplication kernel match a scalar reference across edge sizes and non-divisible tiles?

Listing reviewed · source terms apply
Software

TRL

Upstream project repository

Language-model post-training components for controlled comparisons of supervised and preference-based optimization objectives.

Investigate Does a chosen preference-loss implementation match a directly specified scalar reference on two synthetic response pairs?

Listing reviewed · source terms apply
Datasets

Ultrasonic flowmeter diagnostics

UCI Machine Learning Repository

Ultrasonic instrument signals for examining diagnostic classifications and sensor drift.

Investigate How does flowmeter diagnosis change when operating conditions are held out?

Listing reviewed · source terms apply
Datasets

UR3 CobotOps

UCI Machine Learning Repository

Collaborative-robot operating records for studying condition changes and sequential prediction.

Investigate How does robot-operation detection change when full task sessions are held out?

Listing reviewed · source terms apply
Datasets

Urban Land Cover

UCI Machine Learning Repository

Urban image-derived features for studying land-cover classification across spatial units.

Investigate How does urban land-cover performance change under spatially grouped evaluation?

Listing reviewed · source terms apply
Datasets

Vehicle routing and scheduling problems

UCI Machine Learning Repository

Courier-service operational observations for examining feature scaling and small-sample clustering.

Investigate How stable are courier-operation clusters when vehicle category and service difficulty are encoded differently?

Listing reviewed · source terms apply
Datasets

Wall-Following Robot Navigation Data

UCI Machine Learning Repository

Robot proximity-sensor observations for testing navigation-state classification.

Investigate Can fewer proximity sensors preserve wall-following class recall under sequence-aware splitting?

Listing reviewed · source terms apply
Datasets

Water Treatment Plant

UCI Machine Learning Repository

Treatment-plant process measurements for studying operating-state detection and missingness.

Investigate How does water-treatment operating-state detection change under time-respecting splits?

Listing reviewed · source terms apply
Datasets

Wave Energy Converters

UCI Machine Learning Repository

Wave-energy converter layouts and simulated output for studying engineering surrogate models.

Investigate How does predicted wave-farm output generalize to held-out layout families?

Listing reviewed · source terms apply
Datasets

Waveform Database Generator (Version 1)

UCI Machine Learning Repository

Generated waveform examples for examining noisy multiclass learning with a documented generator.

Investigate Does waveform classification degrade predictably as irrelevant features are added in a frozen follow-up design?

Listing reviewed · source terms apply
Software

Weights & Biases Python SDK

Upstream project repository

Client tooling for experiment logging and artifact lineage, useful for studying what metadata a run actually records.

Investigate Can an explicitly offline run preserve a minimal parameter-and-metric manifest without transmitting research data?

Listing reviewed · source terms apply
Datasets

Wilt

UCI Machine Learning Repository

Remote-sensing features and tree-condition labels for examining imbalanced ecological classification.

Investigate How does wilt detection performance change when minority-class recall is separated from total accuracy?

Listing reviewed · source terms apply

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