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

BigCode Evaluation Harness

Upstream project repository

Evaluation harness for code language models with task-specific generation and execution workflows.

Investigate Can a chosen task adapter preserve generation settings, sample identity and execution status through evaluation?

Listing reviewed · source terms apply
Datasets

Bike Sharing

UCI Machine Learning Repository

Aggregate bicycle-rental counts and contextual covariates for auditing demand forecasts.

Investigate Does a calendar-aware bike-demand baseline outperform persistence on the final chronological holdout?

Listing reviewed · source terms apply
Software

bitsandbytes

Upstream project repository

Low-precision tensor and optimizer components for investigating memory and numerical-error tradeoffs.

Investigate How does one supported quantization configuration change a small fixed matrix product relative to a high-precision reference?

Listing reviewed · source terms apply
Datasets

Bosch CNC Machining Dataset

UCI Machine Learning Repository

Machining measurements for studying industrial condition recognition under grouped acquisition.

Investigate How does machining-state classification change when machine or recording runs are held out?

Listing reviewed · source terms apply
Datasets

Car Evaluation

UCI Machine Learning Repository

A structured car-rating decision problem useful for checking learned rules against declared categories.

Investigate Do simple decision rules generalize to withheld car-attribute combinations?

Listing reviewed · source terms apply
Datasets

Carbon Nanotubes

UCI Machine Learning Repository

Nanotube configuration coordinates for investigating geometric relaxation surrogates.

Investigate How well does a nanotube coordinate surrogate generalize to withheld structural configurations?

Listing reviewed · source terms apply
Software

ccdproc

Upstream project repository

Processing steps for CCD astronomical images, including calibration and image combination.

Investigate Does a fixed CCD calibration sequence recover the generated signal and propagate the declared mask behavior?

Listing reviewed · source terms apply
Datasets

Challenger USA Space Shuttle O-Ring

UCI Machine Learning Repository

Historical shuttle component observations for inspecting extrapolation and small-sample uncertainty.

Investigate How strongly does the fitted O-ring damage relationship depend on the coldest observations?

Listing reviewed · source terms apply
Datasets

Chemical Composition of Ceramic Samples

UCI Machine Learning Repository

Ceramic chemistry measurements for investigating small-sample material-group identification.

Investigate How stable are ceramic composition groups under resampling and measurement-scale changes?

Listing reviewed · source terms apply
Datasets

Chess (King-Rook vs. King)

UCI Machine Learning Repository

Chess endgame positions for examining generalization under exact combinatorial constraints.

Investigate How does an endgame classifier perform on held-out position symmetries after duplicate-equivalence checks?

Listing reviewed · source terms apply
Software

Chex

Upstream project repository

Assertions and testing utilities for JAX programs, useful for expressing shape, type and transformation expectations.

Investigate Do declared shape and tree invariants detect deliberately malformed inputs to a tiny numerical function?

Listing reviewed · source terms apply
Datasets

Climate Model Simulation Crashes

UCI Machine Learning Repository

Climate-model run parameters and crash labels for examining failure prediction in simulation campaigns.

Investigate Can a small classifier identify climate simulation crashes under a frozen class-balanced evaluation?

Listing reviewed · source terms apply

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