MetaboAnalystR
The R engine behind MetaboAnalyst closes the gap from raw spectra to biological interpretation
Comparison · Analytics
cIRT vs tulpaRatio
A side-by-side editorial comparison of cIRT and tulpaRatio — release velocity, themes, recent moves, and the top alternatives to consider.
Shared themes:r-package
cIRT vs tulpaRatio: at a glance
What is cIRT?
A choice-based IRT model published once in 2019 and kept compiling ever since
cIRT implements Choice Item Response Theory, jointly modelling which item a respondent picks and how they perform on it — the setting where subjects choose between a harder and an easier question and the choice itself carries information. It comes out of the TMSA Lab, is built on Rcpp and RcppArmadillo, and has had one substantive release since reaching CRAN. Everything after early 2019 is build-system and toolchain upkeep.
What is tulpaRatio?
A Bayesian ratio-modelling package that threw out its Stan dependency and wrote its own sampler
ratiod models ratios, rates and proportions hierarchically, with the stated position that a ratio is a derived quantity and inference should run on the latent numerator and denominator processes rather than their quotient. The 1.0.0 release shipped a native HMC/NUTS backend, removing the Stan dependency that packages in this space normally take as given. Everything since has been sampler optimisation, benchmarked against the Stan implementations it replaced.
cIRT vs tulpaRatio: editorial side-by-side
cIRT
0.0ANALYTICS
A choice-based IRT model published once in 2019 and kept compiling ever since
◆ Current state
cIRT implements Choice Item Response Theory, jointly modelling which item a respondent picks and how they perform on it — the setting where subjects choose between a harder and an easier question and the choice itself carries information. It comes out of the TMSA Lab, is built on Rcpp and RcppArmadillo, and has had one substantive release since reaching CRAN. Everything after early 2019 is build-system and toolchain upkeep.
◆ Where it's heading
The package's whole functional history fits in a two-day window in January 2019, when the CRAN release and its immediate follow-ups were tagged in one batch, followed a day later by a release enabling C++11 and OpenMP and fixing the choice generation procedure. Since then the releases track other people's deprecations: Armadillo dropping conversions, RcppArmadillo requiring a different Makevars, R raising its floor. The 2025 release is entirely of that kind, down to swapping the README to Quarto.
◆ Prediction
The dependency floors were just raised to current Rcpp and RcppArmadillo, so the next release is most likely the one after Armadillo deprecates something else.
tulpaRatio
0.0ANALYTICS
A Bayesian ratio-modelling package that threw out its Stan dependency and wrote its own sampler
◆ Current state
ratiod models ratios, rates and proportions hierarchically, with the stated position that a ratio is a derived quantity and inference should run on the latent numerator and denominator processes rather than their quotient. The 1.0.0 release shipped a native HMC/NUTS backend, removing the Stan dependency that packages in this space normally take as given. Everything since has been sampler optimisation, benchmarked against the Stan implementations it replaced.
◆ Where it's heading
The feed reads as one architectural bet followed by the work to justify it. After the native backend landed, the releases are a steady march of gradient and adaptation work — hand-coded gradients for more model families, L-BFGS mass matrix adaptation, an O2 build — each measured as a speed multiple against Stan. Coverage is tracked openly as a fraction (48 of 60 hand-coded configs), and unresolved problems are named rather than buried, including a deferred GP spatial bug.
◆ Prediction
The hand-coded gradient coverage count is the visible backlog, so the next releases most likely close the remaining configs and resolve the GP spatial issue that the benchmark release explicitly deferred.
Alternatives to cIRT and tulpaRatio
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 cIRT or tulpaRatio.
fmtr
Rebuilding SAS's formatting layer in R, one format specification at a time
betaselectr
Standardised coefficients for models where standardising everything is wrong — but the feed only links out
SSN2
Stream-network spatial models learning to run on data that no longer fits in memory
BiocManager
Bioconductor's installer, frozen at 1.30.x and tuned almost entirely through environment variables
dcurves
Decision curve analysis, settled since 2022 and now moving only when its neighbours do
See all cIRT alternatives → · See all tulpaRatio alternatives →
Recent activity from cIRT and tulpaRatio
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 6mo agotulpaRatioHand-coded gradients reach binomial zero-inflated and hurdle models
- 6mo agotulpaRatioGaussian process sampling reaches roughly 4x Stan
- 7mo agotulpaRatioL-BFGS mass matrix adaptation for MSGP models
- 7mo agotulpaRatioBenchmarks published for 35 of 40 model configurations
- 7mo agotulpaRatioFirst stable release ships a native HMC/NUTS backend, no Stan required ⚡
- 10mo agocIRTArmadillo deprecations cleared, build config modernised
- 4y agocIRTperson() argument fix and dependency floor raise
- 6y agocIRTpkgdown site added, CI moved to GitHub Actions
- 7y agocIRTOpenMP enabled and the choice generation bug fixed
- 7y agocIRTcIRT 1.0.0: Initial Package Released to CRAN
- 7y agocIRTChoice matrix gains hard and easy question ids
Frequently asked questions
What is the difference between cIRT and tulpaRatio?
Both compete on the same themes — r-package — within Analytics. cIRT and tulpaRatio 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.
Is cIRT better than tulpaRatio?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. cIRT and tulpaRatio 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.
What are the best alternatives to cIRT?
Top cIRT alternatives in Analytics are ranked by recent ship velocity. Browse the "cIRT alternatives" section above for the current picks, or visit /alternatives/cirt for the full list with editorial commentary on each.
What are the best alternatives to tulpaRatio?
Top tulpaRatio alternatives in Analytics are ranked by recent ship velocity. Browse the "tulpaRatio alternatives" section above for the current picks, or visit /alternatives/tulparatio for the full list with editorial commentary on each.