Zoho Creator
Three months on, Zoho is still selling the HDS certification rather than shipping past it.
Comparison · Infra & APIs
exametrika vs sits
A side-by-side editorial comparison of exametrika and sits — release velocity, themes, recent moves, and the top alternatives to consider.
Shared themes:r-package
exametrika vs sits: at a glance
What is exametrika?
exametrika breaks its own numbers to fix them, and ships the fit statistic nominal data lacked.
exametrika is an R psychometrics package covering IRT, latent class and rank analysis, and biclustering. Version 2.0.0 is a deliberate break: an EM convergence defect inherited from the reference implementation stopped estimation after as little as one cycle while reporting convergence, so every EM-based model in the package now returns different estimates than it did before. The package no longer reproduces the numbers printed in Shojima (2022), and the maintainer says so directly rather than burying it. The deprecation removals promised since 1.15.0 ride along in the same release, and the package title changed to Test Data Engineering.
What is sits?
An R package for satellite time series just grew a Python API.
sits classifies satellite image time series — building data cubes from cloud archives, training deep learning models on them, and producing land-cover maps. The releases here are dense feature lists in a steady 1.5.x line, and two themes recur in every one: more source collections wired in, and more of the classification pipeline made parallel or chunked. Version 1.5.3 added pysits, a Python API onto the same engine.
exametrika vs sits: editorial side-by-side
exametrika
3.8INFRA · APIS
exametrika breaks its own numbers to fix them, and ships the fit statistic nominal data lacked.
◆ Current state
exametrika is an R psychometrics package covering IRT, latent class and rank analysis, and biclustering. Version 2.0.0 is a deliberate break: an EM convergence defect inherited from the reference implementation stopped estimation after as little as one cycle while reporting convergence, so every EM-based model in the package now returns different estimates than it did before. The package no longer reproduces the numbers printed in Shojima (2022), and the maintainer says so directly rather than burying it. The deprecation removals promised since 1.15.0 ride along in the same release, and the package title changed to Test Data Engineering.
◆ Where it's heading
The consolidation arc that ran through 1.14.0 and 1.15.0 has closed, but not the way the audit trail suggested it would. Rather than pausing new modelling work through the cleanup, 2.0.0 pairs the breaking removals with real capability: M2() and add_M2() bring a limited-information fit statistic with a full margin-based index set, order-restricted estimation becomes the default for Ranklustering on the strength of a higher likelihood, and LCA() picks up nominal and rated data. The correctness fixes share one shape - defects that got worse as data got larger, where a 700-respondent dataset silently merged fields and a 40-item test returned no assignments at all. A two-tier test suite now keeps 3,507 tests in CI while CRAN sees a 17-second subset.
◆ Prediction
With the deprecation backlog cleared and the EM core rewritten, the next releases have room to build on M2() - most plausibly extending the margin-based indices to the models that do not yet report them. Whether the R Journal submission that shaped 1.13.1 and 1.14.0 has landed is not visible in these entries.
sits
0.0INFRA · APIS
An R package for satellite time series just grew a Python API.
◆ Current state
sits classifies satellite image time series — building data cubes from cloud archives, training deep learning models on them, and producing land-cover maps. The releases here are dense feature lists in a steady 1.5.x line, and two themes recur in every one: more source collections wired in, and more of the classification pipeline made parallel or chunked. Version 1.5.3 added pysits, a Python API onto the same engine.
◆ Where it's heading
The package is positioning itself as the interface layer to Earth observation archives rather than as an algorithm library. Each release absorbs another provider — Planetary Computer, Digital Earth Africa and Australia, CDSE, TERRASCOPE, Open Geo Hub, PLANET — so the differentiator is coverage and the uniform cube abstraction over it. The Python API extends the same logic to the language most of that community actually works in. Alongside, the work is increasingly about scale: chunk parallelisation, multicores sampling, GPU classification, WebGL rendering.
◆ Prediction
With collections still being added release over release, expect more providers and continued performance work on the classification and regularisation paths. The open question the entries do not answer is how far pysits tracks the R API, since it appears once and is not mentioned again in later releases.
Alternatives to exametrika and sits
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 exametrika or sits.
Retool
Retool now debugs the apps its agent builds, and versions them across instances.
nuggets
A pattern-mining package that keeps making its own search cheaper rather than wider.
Traefik
Traefik's 2.11 line spends August fixing the names it generates for Kubernetes resources.
NGINX
nginx returns to feature work with PROXY v2 upstream writes, and quietly adds JSON to core.
ESPHome
ESPHome closes the 2026.8 cycle, but the release body is a bare link to the real notes.
See all exametrika alternatives → · See all sits alternatives →
Recent activity from exametrika and sits
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 1d agoexametrikaEM convergence fix changes every estimate; deprecated names removed ⚡
- 1mo agoexametrikaFull-codebase audit fixes silent result corruption, unifies arguments
- 2mo agoexametrikaPlot methods finally forward the graphical parameters they documented
- 3mo agoexametrikaCRAN resubmission: slow tests skipped to fit the check budget
- 3mo agoexametrikaGraphical Lasso and Chatterjee's xi extend the package into network estimation ⚡
- 3mo agoexametrikaFrozen research baseline, never released to CRAN
- 7mo agositsSNIC segmentation, imputation helpers and QGIS palette export
- 8mo agositsOne-line hotfix for a CRAN compiler requirement
- 11mo agositsHotfix: TAE embeddings, MPC token handling, texture divide-by-zero
- 11mo agositsA Python API arrives, alongside SAR texture measures ⚡
- 1y agositsExclusion masks, multiple tiling systems and faster segment classification
- 1y agositsFour more archives wired in, including Digital Earth Africa
Frequently asked questions
What is the difference between exametrika and sits?
Both compete on the same themes — r-package — within Infra & APIs. exametrika is currently shipping more aggressively (velocity 3.8 vs 0.0), with 1 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is exametrika better than sits?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. exametrika is currently shipping more aggressively (velocity 3.8 vs 0.0), with 1 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Infra & APIs products to evaluate alongside.
What are the best alternatives to exametrika?
Top exametrika alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "exametrika alternatives" section above for the current picks, or visit /alternatives/exametrika for the full list with editorial commentary on each.
What are the best alternatives to sits?
Top sits alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "sits alternatives" section above for the current picks, or visit /alternatives/sits for the full list with editorial commentary on each.