cvms
A cross-validation package whose real development has moved to its plotting function
A side-by-side editorial comparison of gkwdist and missSBM — release velocity, themes, recent moves, and the top alternatives to consider.
gkwdist keeps finding that its distributions were returning the wrong numbers.
The package implements the Generalized Kumaraswamy distribution family and its sub-families. The current release fixes six numerical defects, the most serious being that dgkw() returned zero for every input because internal helpers collided with same-named functions in R's public Rmath.h header. Log-likelihoods for three sub-families were also wrong for data near zero due to clamping instead of working in log space.
missSBM returns after four dormant years with a stricter API and a new refinement step.
The package fits stochastic block models to networks with missing data, covering both missing-at-random and informative sampling designs. After a run of releases from 2019 to 2022, the feed goes quiet until this year's 1.1.0, which breaks the control interface, exposes the block split and merge operations as testable instance methods, and adds a node-swap refinement pass that runs after variational convergence.
The package implements the Generalized Kumaraswamy distribution family and its sub-families. The current release fixes six numerical defects, the most serious being that dgkw() returned zero for every input because internal helpers collided with same-named functions in R's public Rmath.h header. Log-likelihoods for three sub-families were also wrong for data near zero due to clamping instead of working in log space.
Every release in this window is correctness work with an unchanged public API — critical MLE fixes in 1.1.3, a CRAN timing-test patch in 1.1.4, numerical corrections in 1.1.5. The recurring theme is that analytically correct formulas were being defeated by implementation details: name collisions, sign errors returning negative infinity where positive was required, and clamping thresholds that destroyed precision in the tails. Test infrastructure added in 1.1.2 validates analytical derivatives against numerical differentiation, which is how several of these were caught.
Expect further validation-driven fixes rather than new distributions, since the derivative-checking suite added earlier is still surfacing defects in existing routines.
The package fits stochastic block models to networks with missing data, covering both missing-at-random and informative sampling designs. After a run of releases from 2019 to 2022, the feed goes quiet until this year's 1.1.0, which breaks the control interface, exposes the block split and merge operations as testable instance methods, and adds a node-swap refinement pass that runs after variational convergence.
The new release is maintenance-driven in the best sense: it targets the parts of the codebase that were hard to test or easy to misuse. Replacing free-form control lists with a function of named, defaulted arguments turns silent typos into errors, and pulling the exploration logic out of the collection class makes the search algorithm independently testable without changing it. The polish step addresses a known weakness, reaching individually misclassified nodes that split and merge moves cannot fix.
Given the gap before this release, the near-term question is whether the cadence resumes at all; the refactoring it contains would support further algorithmic work if it does.
Other Infra & APIs products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either gkwdist or missSBM.
A cross-validation package whose real development has moved to its plotting function
A statistics-formatting helper in maintenance mode, tracking R-devel one fix at a time
pathfindR dropped Java from its subnetwork search and rebuilt it in C++
A microbiome analysis framework quietly grew a metabolomics half
A calibration toolkit that found its core PEST++ bridge had never actually run
CloudStack's feed shows two LTS branches maintained in parallel and little else
See all gkwdist alternatives → · See all missSBM alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — r-package — within Infra & APIs. gkwdist and missSBM are shipping at a similar cadence (velocity 2.5 vs 2.5, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. gkwdist and missSBM are shipping at a similar cadence (velocity 2.5 vs 2.5, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Infra & APIs products to evaluate alongside.
Top gkwdist alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "gkwdist alternatives" section above for the current picks, or visit /alternatives/gkwdist for the full list with editorial commentary on each.
Top missSBM alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "missSBM alternatives" section above for the current picks, or visit /alternatives/misssbm for the full list with editorial commentary on each.