bbotk
bbotk is generalizing from an optimizer toolkit into an evaluation framework.
Comparison · Analytics
Fulcrum vs tune
A side-by-side editorial comparison of Fulcrum and tune — release velocity, themes, recent moves, and the top alternatives to consider.
Fulcrum vs tune: at a glance
| Feature | Fulcrum | tune |
|---|---|---|
| Sector | Analytics | Analytics |
| Velocity score | 6.3 | 0.0 |
| Sparks · 30d | 0 | 0 |
| Top themes | field-data-collection, esri-arcgis, offline-maps, on-device-inference | hyperparameter-tuning, tidymodels, parallelism, postprocessing |
| Last editorial update | 15h ago | 49m ago |
| Website | — | Visit → |
What is Fulcrum?
Fulcrum's mobile train is all Esri migration cleanup, with on-device inference quietly changing format.
Fulcrum ships iOS, Android, and web releases on a near-weekly cadence, and this stretch is dominated by mapping work following the Google Maps retirement announced for September. Recent builds upgraded to ArcGIS SDK 300.0.0, moved the web map engine to current ArcGIS and deck.gl versions, and worked through the resulting stability issues — basemap loading, location resolution, black map screens, panning and zooming performance. The most consequential change is easy to miss: ONNX support for on-device machine learning inference was removed in favor of a new INFERENCE format that reads labels from an uploaded labels.txt.
What is tune?
tune extends tuning past the model itself to postprocessors, and adds a second parallel backend
tune runs hyperparameter search for tidymodels. Version 2.0.0 rewrote tune_grid() to make postprocessing tunable alongside preprocessing and the model, changed the .config naming scheme to match, and added mirai as a parallel backend next to future. Version 2.1.0 followed with quantile regression support and a replacement Gaussian process engine.
Fulcrum vs tune: editorial side-by-side
Fulcrum
6.3ANALYTICS
Fulcrum's mobile train is all Esri migration cleanup, with on-device inference quietly changing format.
◆ Current state
Fulcrum ships iOS, Android, and web releases on a near-weekly cadence, and this stretch is dominated by mapping work following the Google Maps retirement announced for September. Recent builds upgraded to ArcGIS SDK 300.0.0, moved the web map engine to current ArcGIS and deck.gl versions, and worked through the resulting stability issues — basemap loading, location resolution, black map screens, panning and zooming performance. The most consequential change is easy to miss: ONNX support for on-device machine learning inference was removed in favor of a new INFERENCE format that reads labels from an uploaded labels.txt.
◆ Where it's heading
This is a platform consolidation being paid down one point release at a time. Having committed to Esri, Fulcrum is absorbing the instability that came with it, and each release reads as fixes to symptoms of the same migration. Underneath, the offline and field-capture story continues to get real attention — downloaded offline map layers can now be updated in place, and Photo FastFill moved to background processing so it no longer blocks editing.
◆ Prediction
Expect the release notes to stay fix-dominated through the September Google Maps cutoff, with the migration-related map defects tapering after it passes. Photo FastFill leaving early access is the most likely next substantive item.
tune
0.0ANALYTICS
tune extends tuning past the model itself to postprocessors, and adds a second parallel backend
◆ Current state
tune runs hyperparameter search for tidymodels. Version 2.0.0 rewrote tune_grid() to make postprocessing tunable alongside preprocessing and the model, changed the .config naming scheme to match, and added mirai as a parallel backend next to future. Version 2.1.0 followed with quantile regression support and a replacement Gaussian process engine.
◆ Where it's heading
Two migrations run through this timeline. The tunable surface keeps widening - first censored regression as a mode, then postprocessors via tailor - so that a candidate is now a preprocessor, model and postprocessor triple rather than just a model. The parallel story has moved from foreach to future and now to mirai, each step deprecating the last. Neither is finished.
◆ Prediction
Expect the foreach path to be removed outright, and the postprocessing surface to grow as tailor gains more steps; the GauPro switch will likely need follow-up as its behavior differs from the old engine.
Alternatives to Fulcrum and tune
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 Fulcrum or tune.
bayesplot
bayesplot keeps widening its posterior-check catalogue while absorbing each ggplot2 break.
animation
Contribution-driven maintenance on a package whose last structural change was magick support.
pins
pins keeps adding a storage backend per release while retiring its original API
tsibble
tsibble shipped one release in five and a half years - the data structure is finished
yardstick
yardstick made fairness metrics a first-class part of tidymodels evaluation
See all Fulcrum alternatives → · See all tune alternatives →
Recent activity from Fulcrum and tune
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 23h agoFulcrumAndroid: update offline map layers in place, non-blocking Photo FastFill
- 1d agoFulcrumiOS fix: slow location resolution blocked record saves
- 6d agoFulcrumWeb: SSO email wording and ArcGIS/deck.gl version bumps
- 7d agoFulcrumAndroid fixes: ArcGIS stability, signature button, photo markup
- 7d agoFulcrumiOS fixes: basemap loading and black map screen
- 8d agoFulcrumiOS: ArcGIS SDK 300.0.0 and ONNX replaced by a new INFERENCE format
- 3mo agotuneQuantile regression tuning; Bayesian search moves to GauPro
- 9mo agotuneFixes int_pctl() with future parallelism on last_fit()
- 11mo agotunePostprocessors become tunable; mirai joins future as a backend ⚡
- 11mo agotuneDevelopment snapshot re-enabling skipped tests
- 1y agotuneWarns on foreach parallelism; space-filling grids by default
- 2y agotuneFixes parallel tuning errors under multisession plans
Frequently asked questions
What is the difference between Fulcrum and tune?
They serve adjacent needs but don't currently overlap on shipped themes. Fulcrum is currently shipping more aggressively (velocity 6.3 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 Fulcrum better than tune?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Fulcrum is currently shipping more aggressively (velocity 6.3 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 Fulcrum?
Top Fulcrum alternatives in Analytics are ranked by recent ship velocity. Browse the "Fulcrum alternatives" section above for the current picks, or visit /alternatives/fulcrum for the full list with editorial commentary on each.
What are the best alternatives to tune?
Top tune alternatives in Analytics are ranked by recent ship velocity. Browse the "tune alternatives" section above for the current picks, or visit /alternatives/tune for the full list with editorial commentary on each.