r2rtf
The clinical-report table engine learned Chinese, then learned to leave RTF entirely
Comparison · Analytics
simtrial vs tabnet
A side-by-side editorial comparison of simtrial and tabnet — release velocity, themes, recent moves, and the top alternatives to consider.
simtrial vs tabnet: at a glance
What is simtrial?
A fixed-design trial simulator grew a pluggable test framework, then spent a year proving the numbers
simtrial simulates time-to-event clinical trials and applies the tests used to analyse them — logrank, weighted logrank, MaxCombo, RMST, milestone. The 0.4.0 release turned it from a fixed-sample simulator into a group sequential one and standardised every test behind a common output contract, and the releases since have been about making that machinery correct and fast enough to run at scale. Version 1.0.0 arrived in June 2025 with the API settled and three vignettes explaining both the one-call and build-it-yourself paths.
What is tabnet?
A tabular deep-learning model in R that keeps widening what counts as a tabular task.
tabnet ports the TabNet attentive tabular architecture to R on torch, wired into tidymodels through parsnip so it slots into workflows, tuning, and case weights like any other engine. The model surface has grown well past plain supervised fitting: unsupervised pretraining, missing values in predictors, multi-outcome fitting, hierarchical multi-label classification, and built-in explainability via tabnet_explain(). The 0.9.x line has been consolidating rather than adding, with 0.9.0 finally making hierarchical classification work correctly by accounting for the ancestor matrix.
simtrial vs tabnet: editorial side-by-side
simtrial
0.0ANALYTICS
A fixed-design trial simulator grew a pluggable test framework, then spent a year proving the numbers
◆ Current state
simtrial simulates time-to-event clinical trials and applies the tests used to analyse them — logrank, weighted logrank, MaxCombo, RMST, milestone. The 0.4.0 release turned it from a fixed-sample simulator into a group sequential one and standardised every test behind a common output contract, and the releases since have been about making that machinery correct and fast enough to run at scale. Version 1.0.0 arrived in June 2025 with the API settled and three vignettes explaining both the one-call and build-it-yourself paths.
◆ Where it's heading
Post-1.0 the work is almost entirely statistical correctness and speed, and it is concentrated in sim_gs_n(): one-sided efficacy bounds, stratified targeted-event cut dates, a helper that derives cuttings straight from the design object. Performance moves in one direction throughout — dplyr replaced by data.table, foreach combination replaced by manual assembly, parallelisation added to sim_fixed_n() — because simulation-based operating characteristics are only useful if you can afford enough replications.
◆ Prediction
The recent fixes cluster on stratified and group sequential paths, so the next release most likely continues there rather than adding a new test type. The cut_from_design() helper suggests tighter coupling to gsDesign2 design objects is the direction of travel.
tabnet
2.5ANALYTICS
A tabular deep-learning model in R that keeps widening what counts as a tabular task.
◆ Current state
tabnet ports the TabNet attentive tabular architecture to R on torch, wired into tidymodels through parsnip so it slots into workflows, tuning, and case weights like any other engine. The model surface has grown well past plain supervised fitting: unsupervised pretraining, missing values in predictors, multi-outcome fitting, hierarchical multi-label classification, and built-in explainability via tabnet_explain(). The 0.9.x line has been consolidating rather than adding, with 0.9.0 finally making hierarchical classification work correctly by accounting for the ancestor matrix.
◆ Where it's heading
Two threads run through the release history. The first is task surface — each minor version tends to admit a class of problem the model previously could not express, from missing data to hierarchy to imbalanced binary outcomes. The second is torch-level performance and correctness, visible in the torch_ignite_adam default that cut pretraining time roughly 30% and the fix for optimizers frozen after checkpointing on cuda and mps. Tidymodels integration is treated as a first-class obligation, with parsnip breaking changes tracked release by release.
◆ Prediction
The hierarchical path is the least finished: 0.5.0 introduced it and 0.9.0 only just made it effective, so the next releases most likely extend evaluation and explainability to hierarchical fits rather than adding another task type.
Alternatives to simtrial and tabnet
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 simtrial or tabnet.
DoseFinding
New stewardship at openpharma, then two releases adding the methods MCP-Mod was missing
webmockr
The stubbing library added httr2 support, then spent a year cutting itself free of everything else
crul
crul took mocking back from webmockr and made it a property of the client itself
dendroNetwork
Six releases, six identical bodies — the feed carries the package abstract instead of release notes
chattr
chattr deleted every LLM integration it had written and outsourced the lot to ellmer
See all simtrial alternatives → · See all tabnet alternatives →
Recent activity from simtrial and tabnet
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 21d agotabnetvip dependency moves to r-universe
- 2mo agotabnetHierarchical classification made effective, augment() added
- 6mo agotabnetentmax15 and sparsemax15 masks, AUM loss for imbalanced data
- 8mo agosimtrialOne-sided efficacy bound and stratified cut date corrected
- 11mo agosimtrialsim_gs_n moved to data.table; stratified design example added
- 1y agosimtrial1.0.0 settles the wlr interface and documents both simulation paths
- 1y agotabnetBugfix release for R 4.5 and dials tuning
- 1y agosimtrialMilestone Z-score denominator corrected; parallel sim_fixed_n arrives
- 2y agotabnetCase weights and warm-start parameters via parsnip
- 2y agosimtrialChecks pass without Suggests dependencies
- 2y agosimtrialRMST and milestone tests, plus a user-definable cut and test framework ⚡
- 2y agotabnetHierarchical multi-label classification via data.tree ⚡
Frequently asked questions
What is the difference between simtrial and tabnet?
They serve adjacent needs but don't currently overlap on shipped themes. tabnet is currently shipping more aggressively (velocity 2.5 vs 0.0), with 0 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 simtrial better than tabnet?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. tabnet is currently shipping more aggressively (velocity 2.5 vs 0.0), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Analytics products to evaluate alongside.
What are the best alternatives to simtrial?
Top simtrial alternatives in Analytics are ranked by recent ship velocity. Browse the "simtrial alternatives" section above for the current picks, or visit /alternatives/simtrial for the full list with editorial commentary on each.
What are the best alternatives to tabnet?
Top tabnet alternatives in Analytics are ranked by recent ship velocity. Browse the "tabnet alternatives" section above for the current picks, or visit /alternatives/tabnet for the full list with editorial commentary on each.