The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

leafwax 0.2.7

CRAN resubmission polish.

• Updated DESCRIPTION formatting for CRAN: software/service names are quoted as 'Stan' and 'Zenodo', and the data-deposit reference now uses Bradley (2026) <doi:10.5281/zenodo.20085465>.
• Replaced \dontrun{} examples with executable \donttest{} or unwrapped examples, with temporary cache directories and quiet output where examples touch downloads or cache state.
• Added the missing return-value documentation for print.leafwax_posterior().
• Converted the remaining unguarded ensemble progress output to message().
• Updated package documentation for the precipitation-isotope calibration slope.

leafwax 0.2.6

Initial CRAN release.

Features

• Bayesian inversion of leaf-wax δ²H to precipitation δ²H using spatially-aware hierarchical calibrations (14 model variants from Bradley 2026, in prep). Posteriors are pre-computed in Stan and shipped as serialized draws, so prediction does not require Stan.
• Four-level claim taxonomy via assess_claim(): from analytical-noise thresholds (Level 1) through directional hydroclimate change (Level 2, via corroborating evidence OR the vegetation-only envelope from compute_vegetation_envelope()), quantitative magnitude (Level 3), and unique attribution to precipitation isotopes (Level 4).
• Per-record change detection (detect_change()) with autocorrelation-adjusted thresholds and full posterior propagation through invert_d2H(). The within-record detection threshold decomposes the variance of the difference between two single samples as 2 * sigma_residual^2 * (1 - rho_t) + 2 * sigma_analytical^2, applying the lag-1 autocorrelation factor only to the residual term (analytical measurement error is independent between samples).
• 100-draw preview posteriors ship with the package; full 1000-draw posteriors are downloaded from a versioned Zenodo deposit on first use (DOI: 10.5281/zenodo.20085465).

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.