Find your next starting point.

ReScience C

A replication about hierarchical shrinkage as regularization for tree-based predictive methods.

Investigate How do shrinkage strength, prediction error and tree-based explanations vary under nested cross-validation?

ReScience C

A replication about calibration and predictive uncertainty in deep neural networks, including mixup in its source keywords.

Investigate How do log loss, calibration summaries and selective-prediction error compare under a fixed validation and test split?

ReScience C

A replication about graph representations and fairness-aware data augmentation, with separate upstream code and data records.

Investigate Does the performance–fairness tradeoff persist under held-out graph splits chosen before training?

ReScience C

A Python replication concerning network deconvolution; the upstream record links an ImageNet data source whose access and redistribution require separate review.

Investigate Which comparison in the article can be tested using a rights-cleared small image dataset while retaining a clearly stated scope limit?

ReScience C

A replication that connects object detection with knowledge graphs and semantic consistency.

Investigate What tradeoff appears between detection error and a frozen semantic-consistency rule on a rights-cleared image subset?

ReScience C

A replication concerning label smoothing in neural-network training.

Investigate How does smoothing strength alter accuracy, log loss and calibration on a fixed validation protocol?

ReScience C

A replication of exploration in model-based reinforcement learning using estimates of learning progress.

Investigate Does an exploration advantage survive across fixed environment seeds when interaction budgets are equal?

UCI Machine Learning Repository

Marine morphometrics for studying relationships between body measurements and growth indicators.

Investigate How does an abalone ring-count baseline change when sex is omitted and error is reported by size band?

Upstream project repository

Multi-environment agent benchmark repository for investigating task adapters and evaluation consistency.

Investigate Can a single reviewed environment separate malformed agent actions, infrastructure errors and genuine task failures?

UCI Machine Learning Repository

A documented artificial maintenance dataset for testing rare-failure evaluation and shortcut learning.

Investigate How do maintenance predictions change after removing variables that encode the synthetic failure construction?

UCI Machine Learning Repository

Air-quality sensor readings and reference measurements for investigating calibration over time.

Investigate How does a sensor calibration model drift across a chronological air-quality holdout?

UCI Machine Learning Repository

Aeroacoustic measurements for examining nonlinear physical response prediction.

Investigate How does airfoil noise prediction generalize when frequency or flow regimes are withheld?