Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.
Upstream project repository
Evaluation of numerical array expressions with a specialized execution engine.
Investigate Does fused expression evaluation agree with a high-precision reference near cancellation?
Upstream project repository
Evaluation framework and registry for organizing model tasks and inspecting how examples become aggregate scores.
Investigate Does a deterministic synthetic evaluation preserve example order, expected labels and aggregate denominators?
UCI Machine Learning Repository
Network configuration and performance observations for examining engineering response surfaces.
Investigate How does optical-network performance prediction change under configuration-group holdout?
Upstream project repository
Model optimization integrations for investigating the accuracy and latency consequences of a chosen deployment transformation.
Investigate Does one declared export or optimization path preserve a tiny model's outputs within a frozen tolerance?
Upstream project repository
Automated hyperparameter search with trial management, sampling, and pruning methods.
Investigate How do fixed samplers compare after the same number of evaluations on a known multimodal objective?
UCI Machine Learning Repository
Atmospheric predictors and ozone-event labels for inspecting temporally dependent rare-event detection.
Investigate How does ozone-event recall change under chronological splitting and train-only imputation?
UCI Machine Learning Repository
Sensor responses to fragrance samples for examining chemical recognition and repeat-measurement leakage.
Investigate How does perfume recognition change when repeated measurements of a sample stay within one fold?
UCI Machine Learning Repository
Hourly generation measurements for evaluating electricity-supply forecasting across time.
Investigate Does seasonal persistence match a covariate-based generation forecast on a final chronological holdout?
UCI Machine Learning Repository
Hardware challenge-response records for studying generalization in physical-device models.
Investigate How does a challenge-response model generalize when devices or challenge families are held out?
UCI Machine Learning Repository
Generated card hands with rule-based labels for testing rare combinatorial classes.
Investigate Can a poker-hand classifier identify rare hand classes on a split that excludes reordered duplicates?
UCI Machine Learning Repository
City electricity-demand measurements for studying seasonal and multi-zone forecasts.
Investigate Does a zone-aware load forecast improve on seasonal persistence in a chronological Tetouan holdout?
UCI Machine Learning Repository
Artificial oscillatory sequences for testing methods against controlled temporal structure.
Investigate Can a period-aware baseline outperform persistence on a fixed pseudo-periodic holdout?
Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.