Research, software, data and methods. Inspect the context, compare your options, and take a useful next step.
UCI Machine Learning Repository
Agent-swarm descriptors for studying emergent-state recognition in simulation data.
Investigate Can a swarm-state model generalize to withheld simulation parameter settings?
Upstream project repository
Agent tooling for interacting with code repositories and attempting software engineering tasks through a controlled interface.
Investigate Does a deterministic toy repository expose whether an agent's claimed edit matches the actual patch and test evidence?
Upstream project repository
Software issue-resolution benchmark and evaluation tooling for studying patch assessment and reproducibility.
Investigate Can one explicitly licensed fixture demonstrate that patch application and test-result collection preserve the original issue/task identity?
UCI Machine Learning Repository
Electrical-machine operating measurements for examining bounded response prediction.
Investigate How does synchronous-machine regression generalize to withheld excitation or load regions?
UCI Machine Learning Repository
Constructed circular point groups for examining the limits of distance-based clustering.
Investigate Can clustering methods recover the documented circle groups, and how sensitive are results to distance metric and scale?
UCI Machine Learning Repository
Generated process-control sequences for comparing anomaly-shape classification methods.
Investigate Which synthetic control-chart patterns are confused by a small feature-based baseline?
Executable Science local pilot drafts
Generate 128 regression observations with known coefficients, a declared Gaussian noise process, and a fixed train/test split, together with a small reference fit.
Investigate Can another implementation recover the reference fit and evaluate predictions without changing the test split?
UCI Machine Learning Repository
Completed board states for testing learned combinatorial concepts against inspectable rules.
Investigate Can a tic-tac-toe classifier generalize when symmetry-equivalent boards remain in the same split?
Upstream project repository
Metrics for tensor-based learning systems, useful for testing reductions, state accumulation and distributed aggregation.
Investigate Does a selected classification metric match a hand-built confusion matrix across uneven batch partitions?
UCI Machine Learning Repository
Relational train descriptions for investigating compact logical classification rules.
Investigate Can the published train labels be modeled with a minimal auditable rule set under leave-one-out evaluation?
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?
Recorded license evidence is scoped to each source; it is not a blanket permission or a verification result.