STACAS
Single-cell batch correction that learned to use cell labels, then spent three releases chasing Seurat.
A side-by-side editorial comparison of intsurv and skylight — release velocity, themes, recent moves, and the top alternatives to consider.
A Cox cure-rate model package woke up after four years to simplify its own interface.
intsurv fits Cox cure rate models for right-censored survival data where event status may be uncertain — the case where you cannot tell whether a subject experienced the event or was never susceptible to it. The core has been stable since 2019: cox_cure() and its regularized counterpart cox_cure_net(), plus a weighted concordance index and a data simulator. After more than four years without a release, version 0.3.0 arrived in September 2025 and restructured how those two functions are configured rather than adding capability.
A frozen astronomical model quietly became the inner loop of its sibling's optimizer.
skylight returns sun and moon illuminance, azimuth and altitude for a given date, time and location, implemented as a near-verbatim transcription of a 1987 US Naval Observatory circular. The model formulation has not changed since the initial 2022 release and the author states so explicitly. Everything shipped since has been packaging, citation and speed: v1.3 moved the main routine from R to C++, and v1.4 removed a parameter check that was flooding the console with messages.
intsurv fits Cox cure rate models for right-censored survival data where event status may be uncertain — the case where you cannot tell whether a subject experienced the event or was never susceptible to it. The core has been stable since 2019: cox_cure() and its regularized counterpart cox_cure_net(), plus a weighted concordance index and a data simulator. After more than four years without a release, version 0.3.0 arrived in September 2025 and restructured how those two functions are configured rather than adding capability.
The package has reached the point where the methods are settled and the remaining work is ergonomics. Moving control parameters, M-step settings and penalty specification into cox_cure.control(), cox_cure.mstep() and cox_cure_net.penalty() follows the established R convention of separating tuning from the model formula, and it arrives long after the arguments accumulated. The C++ headers were placed in inst/include as early as 2019 so other packages could link against them, which suggests the implementation was always intended to be reused.
The gap between 0.2.2 and 0.3.0 makes cadence a poor basis for prediction. What the entries do support is that the interface rework is unfinished business rather than a prelude to new methods, so consolidation around the new helper functions is the likelier next step.
skylight returns sun and moon illuminance, azimuth and altitude for a given date, time and location, implemented as a near-verbatim transcription of a 1987 US Naval Observatory circular. The model formulation has not changed since the initial 2022 release and the author states so explicitly. Everything shipped since has been packaging, citation and speed: v1.3 moved the main routine from R to C++, and v1.4 removed a parameter check that was flooding the console with messages.
This is a reference implementation of a published algorithm rather than a product accumulating features, and it is being maintained that way. The movement that does occur is driven from downstream: the C++ port was written for the inverse-modelling loop in the sibling skytrackr package, which calls skylight repeatedly during optimization. That reframes skylight from a standalone calculator into the compute kernel another package's fitting routine depends on.
With the model formulation deliberately fixed and the C++ path already in place, the next release is most likely another small maintenance fix. The entries give no indication of planned new capability.
Other Analytics 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 intsurv or skylight.
Single-cell batch correction that learned to use cell labels, then spent three releases chasing Seurat.
A debugger for ggplot2's internals, hardening its grip as the internals it traces keep moving.
A univariate density estimator that added zero-inflated data and reopened its C++ API to do it.
Stationary vine copulas for time series, released in lockstep with the rest of Nagler's vine stack.
A single-purpose ggplot2 extension that has spent six years tracking ggplot2 instead of growing.
A Star Trek data package that became a Memory Alpha web client and has been patching scrapers ever since.
See all intsurv alternatives → · See all skylight alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — r-package — within Analytics. intsurv and skylight are shipping at a similar cadence (velocity 0.0 vs 0.0, 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. intsurv and skylight are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Analytics products to evaluate alongside.
Top intsurv alternatives in Analytics are ranked by recent ship velocity. Browse the "intsurv alternatives" section above for the current picks, or visit /alternatives/intsurv for the full list with editorial commentary on each.
Top skylight alternatives in Analytics are ranked by recent ship velocity. Browse the "skylight alternatives" section above for the current picks, or visit /alternatives/skylight for the full list with editorial commentary on each.