9 projects
daftar
Record what produced each computational result: environment, code, parameters, seeds, inputs.
tarjuman
Run NeuroML 2 models on the Jaxley simulator: GPU-accelerated, differentiable biophysical simulation
ayna
Know whether your inferred neural dynamics are real, before you interpret them. Diagnoses underfitting, feature invention and dynamical misattribution in data-driven dynamics models.
baghban
Check, draw and compare Bonsai workflows on any machine, before the rig runs.
miras
Cultural inheritance, simulated and interrogated: agent-based models of cultural evolution and a check of whether your study design can recover their parameters.
nezaret
Find MONAI pipeline and dataset faults that do not raise errors: misaligned labels, interpolated class maps, evaluation that peeks at the ground truth, patients leaking across splits, rankings that hinge on a scoring convention.
mihenk
A touchstone for discovered equations: check whether the law PySINDy found is real before you interpret it.
ayar
Assay your spike-sorted finding before you publish: detect sorting artifacts and test whether your result survives them.
raftaar
Know what your robot demonstrations will teach, before you train. Predicts which policy class will fail on a dataset, and where.