AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
JAX-native data assimilation inference — seven peer analysis methods built on pipekit-cycle protocols.
Translation pending
Developer toolsPython · MakefileGitHub @jejjohnsonOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Loading the full README. The saved excerpt is shown below.
Variational data assimilation in JAX — seven analysis methods, one cost function, zero hand-written adjoints.
Optimal interpolation, 3DVar, strong- and weak-constraint 4DVar, incremental
4DVar, 4DVarNet and amortized posteriors are the same estimation problem
solved under different assumptions. vardax implements all seven as peer
equinox modules over a shared
set of seams — observation operator, background covariance, forward model,
minimiser, adjoint — so switching method is a constructor change, not a
rewrite.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Variational data assimilation in JAX — seven analysis methods, one cost function, zero hand-written adjoints.
Optimal interpolation, 3DVar, strong- and weak-constraint 4DVar, incremental
4DVar, 4DVarNet and amortized posteriors are the same estimation problem
solved under different assumptions. vardax implements all seven as peer
equinox modules over a shared
set of seams — observation operator, background covariance, forward model,
minimiser, adjoint — so switching method is a constructor change, not a
rewrite.Read the full README ↗