Find your next starting point.

ReScience C

A replication of tensor Monte Carlo particle methods, with TensorFlow identified in source keywords.

Investigate At equal particle and compute budgets, how does estimator error compare with a tractable reference?

ReScience C

A replication about Bayesian filtering with nonlinear, non-Gaussian observations using a discriminative Kalman filter.

Investigate How do filtering error and interval coverage change as observation noise departs from a Gaussian model?

ReScience C

A Julia replication of an abstract evolutionary model with vertical and horizontal pathogen transmission.

Investigate Can a bounded numerical audit reproduce the model's reported equilibrium calculation with documented solver tolerances?

ReScience C

A Julia replication about principal components of natural images.

Investigate How do the leading subspaces change when centering and scaling choices are varied explicitly?

ReScience C

An R replication of Thompson sampling for bandits whose arms have a cluster structure.

Investigate When the assumed clusters are deliberately incorrect, how does cumulative regret change at a fixed sampling budget?

ReScience C

A C++ replication about wake structure and propulsive performance for pitching and rolling plates in computational fluid dynamics.

Investigate Which force or wake statistic can be subjected to a bounded mesh-and-time-step convergence audit?

ReScience C

A replication concerning variational-autoencoder approximation error, the ELBO and exponential-family models.

Investigate On a tractable latent-variable model, how large is the gap between the computed ELBO and an independently evaluated log likelihood?

ReScience C

A replication of variational sparse coding, linking latent-variable inference with sparse representations.

Investigate How do reconstruction error and sparsity change as a declared regularization or prior setting varies?

ReScience C

A C replication revisiting network-simulation accuracy in the SimGrid framework.

Investigate Can a bounded synthetic topology expose where the selected simulation model departs from an analytic timing baseline?

ReScience C

A C replication about computing volumes of polytopes.

Investigate Can the implementation recover known simplex and box volumes across controlled coordinate scales?

ReScience

A replication of weighted Voronoi stippling, a geometric method for distributing sample points according to image intensity.

Investigate How closely do generated stipple densities match evaluator-defined synthetic intensity maps at fixed point counts?

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?