Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.
Upstream project repository
Function-result caching, persistence, and parallel execution helpers used in scientific Python workflows.
Investigate Does a parameterized deterministic preprocessing task preserve results across fresh and cached runs?
Upstream project repository
Text representations and synchronization for Jupyter notebooks.
Investigate Which explicitly retained notebook fields survive a chosen text-format round trip?
Upstream project repository
Neural-network APIs for examining model behavior across declared computation backends.
Investigate Can the same small model and weights produce consistent predictions across two supported backends?
Upstream project repository
Reference descriptions that expose existing scientific data files through chunked-array interfaces.
Investigate Do generated references resolve the same values as direct access to an immutable local scientific data file?
Upstream project repository
Benchmark repository for evaluating language models on biology and laboratory research knowledge tasks.
Investigate Can a small non-procedural, rights-reviewed subset support an auditable scoring and contamination-risk review?
UCI Machine Learning Repository
Leaf image descriptors for comparing small botanical classification baselines.
Investigate Which leaf classes are unstable under repeated fixed splits and train-only feature scaling?
ReScience C
A replication report on learning from labels that contain errors, with source metadata identifying a Python deep-learning implementation.
Investigate How does a prespecified label-corruption schedule affect held-out accuracy and calibration across fixed seeds?
UCI Machine Learning Repository
A synthetic display-recognition problem with controllable observation noise.
Investigate Does a classifier's error track the documented LED noise mechanism on a frozen evaluation design?
Upstream project repository
Code-model benchmark repository with time-aware task collections for studying evaluation provenance and data contamination.
Investigate Can task timestamps and release identifiers support a reproducible evaluation cut without silently mixing newer problems?
UCI Machine Learning Repository
A constructed feature-selection problem for testing signal recovery among distracting dimensions.
Investigate Does feature selection improve Madelon classification when selection is nested inside training folds?
UCI Machine Learning Repository
Simulated telescope event features for studying signal-background discrimination.
Investigate How do classwise calibration and low-false-positive performance compare for two bounded gamma-event baselines?
UCI Machine Learning Repository
Aggregate road-traffic counts and weather context for evaluating demand forecasts over time.
Investigate Does a seasonal traffic baseline outperform a weather-assisted model on a final chronological holdout?
Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.