Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.
Upstream project repository
Neural-network transformations for JAX, supporting studies of parameter initialization and functional apply behavior.
Investigate Does separating initialization from application preserve a small network's parameter identity and deterministic output?
Upstream project repository
Hierarchical density-based clustering with support for variable-density structure and noise labels.
Investigate How does a fixed density-clustering configuration change as a synthetic bridge connects two point clouds?
Upstream project repository
Python interfaces for HEALPix spherical pixelization and map analysis.
Investigate Do pixel centers and equal-area weights recover the integral of a constant spherical map?
Upstream project repository
Forecast reconciliation and evaluation for hierarchical and grouped time series.
Investigate Do reconciled forecasts satisfy all aggregation constraints in a small synthetic hierarchy?
Upstream project repository
Solvers for linear, mixed-integer, and quadratic optimization problems.
Investigate Do returned transportation plans satisfy supply/demand constraints and a matching dual bound?
UCI Machine Learning Repository
Artificial sampled curves for testing classification of local geometric structure under noise.
Investigate How does hill-versus-valley recognition change across the documented noise conditions?
Upstream project repository
Hidden Markov model estimation and inference with common emission distributions.
Investigate Does the forward-algorithm likelihood equal exhaustive hidden-path summation for a short categorical sequence?
UCI Machine Learning Repository
Radio-survey candidate descriptors for inspecting imbalanced pulsar detection.
Investigate How does pulsar-candidate recall change when thresholds are fixed using training data only?
Upstream project repository
Code-generation evaluation repository for examining functional correctness and pass-at-k estimation on programming tasks.
Investigate Does the pass-at-k aggregation match an independently enumerated finite set of synthetic candidate outcomes?
Upstream project repository
Configuration composition tooling for making experimental variants and overrides inspectable.
Investigate Do nested overrides and a small parameter sweep expand into exactly the prespecified configurations?
UCI Machine Learning Repository
Simulated robot trajectories for preparing a reproducible motion-prediction benchmark.
Investigate Can a trajectory baseline generalize to a held-out simulated robot motion after coordinate and timing audits?
Upstream project repository
Resampling methods and pipeline tools for learning from imbalanced classes.
Investigate How does the placement of resampling affect a fixed imbalanced-class evaluation?
Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.