Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.
Upstream project repository
Transformer inspection tooling for activation capture and controlled interventions in mechanistic interpretability studies.
Investigate Does an intervention at one declared activation site change only the intended computation in a tiny model?
Upstream project repository
Model architecture and tokenization interfaces for studying pretrained transformer behavior and controlled model adaptations.
Investigate Does a fixed tokenizer and model revision give consistent token-level scoring across padding and batching choices?
Upstream project repository
GPU programming language and compiler for developing inspectable tensor kernels and testing numerical/performance tradeoffs.
Investigate Does a tiled matrix-multiplication kernel match a scalar reference across edge sizes and non-divisible tiles?
Upstream project repository
Language-model post-training components for controlled comparisons of supervised and preference-based optimization objectives.
Investigate Does a chosen preference-loss implementation match a directly specified scalar reference on two synthetic response pairs?
Upstream project repository
Storage and analysis of tree sequences representing changing genealogies along genomes.
Investigate Do interval-weighted tree-sequence statistics match direct enumeration of the specified trees?
UCI Machine Learning Repository
Ultrasonic instrument signals for examining diagnostic classifications and sensor drift.
Investigate How does flowmeter diagnosis change when operating conditions are held out?
Upstream project repository
Nonlinear dimensionality reduction based on neighborhood relationships.
Investigate How stable are local-neighborhood preservation metrics across fixed seeds and neighborhood sizes?
Upstream project repository
Propagation of parameter uncertainties and correlations through Python arithmetic expressions.
Investigate Where does first-order uncertainty propagation diverge from a fixed Monte Carlo reference for a nonlinear ratio?
Upstream project repository
Predictive-uncertainty analysis tools for examining calibration, sharpness and scoring on controlled regression predictions.
Investigate Can a fixed synthetic prediction set distinguish calibration changes from changes in interval width?
UCI Machine Learning Repository
Collaborative-robot operating records for studying condition changes and sequential prediction.
Investigate How does robot-operation detection change when full task sessions are held out?
UCI Machine Learning Repository
Urban image-derived features for studying land-cover classification across spatial units.
Investigate How does urban land-cover performance change under spatially grouped evaluation?
Executable Science local pilot drafts
Compare a raw second-moment formula, Welford accumulation, and statistics.pvariance on five large observations with an exact population variance of two.
Investigate How does cancellation affect variance calculations when location is much larger than spread?
Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.