> For the complete documentation index, see [llms.txt](https://docs.rootcause.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rootcause.ai/more-details/digital-twin/configuration.md). # Configuration for Existing Twin The Configuration panel defines what goes into a Digital Twin: the data it runs on, the variables included in causal discovery, the algorithms used, and any prior knowledge about which relationships are known or impossible. Get this right and discovery has a fair chance. Get it wrong and you'll miss real effects or fabricate spurious ones. The Config tab is read-only — it documents the version you are looking at. To change anything, click **Modify model**, which opens the twin builder for this twin; every run there retrains and, except on an untrained 1.0.0, creates a new version and leaves the current one intact in Version History. This page covers a twin that already exists. For the same controls as they appear while first building a twin, see [Configuration to Build Digital Twin](/more-details/build-digital-twin/build-configuration.md). For more context, see [Step 5: Build Digital Twin](/user-guide/creating-digital-twin.md) and [Exploring the Causal Model](/more-details/digital-twin/exploring-causal-model.md). *** ## Opening Configuration Open the twin's **Config** tab from the **Configuration** card on Home. The page documents the current version's configuration; the **Build summary** panel on the right reports the model size, algorithms, and per-stage training times.
The Configuration page for a Churn Digital Twin, captured before the section was renamed and so still labelled Data View, with the Fields list with 20 included and 1 excluded, the SPARC-fast and CausalBART algorithm versions, and a Build summary panel reporting a Static Model with 19 variables, 31 relationships, and stage times totaling 47 seconds

The Config tab. All sections are read-only; Modify model opens the builder to change them, starting a new version.

*** ## Dataset & variables The dataset the twin is built from, shown under a **Dataset** label alongside the Fields list. Changing it triggers a new **major** version, because the twin is now based on different data — as does a change in the underlying data itself, or a change to which fields are included. *** ## Fields Every column from the Dataset, with its data type (Boolean, Category, Number, Date/Time, Array/Set). The header shows the include count ("20 included, 1 excluded" in the example). Use the filter at the top to find a field by name. This list is read-only: each field shows whether it is included or excluded, and changing the selection needs **Modify model** (see [Fields](/more-details/build-digital-twin/build-configuration.md#fields)). Exclude: * **Unique identifiers** (customer\_id, order\_id) — no causal meaning. * **Metadata** (created\_at, updated\_by) — usually irrelevant. * **Redundant fields** that duplicate another column. Include anything you might want to predict, simulate, or trace a causal path through. *** ## Algorithm Versions Two algorithm choices, one per stage: * **Causal Discovery** — builds the graph. Default: **SPARC-fast**; **SPARC** (adaptive multi-stage discovery) is also available. * **Digital Twin** — fits the probabilistic model on top. Default: **CausalBART** (causal Bayesian network simulation) for static and multi-environment static twins, **GAAMT** (temporal causal network simulation) for temporal ones. Multi-environment temporal twins offer **GAAMT** (the default, one temporal network per environment) or **Pooled GAAMT + BART** (one shared network with per-environment corrections). See [Configuration to Build Digital Twin](/more-details/build-digital-twin/build-configuration.md#algorithm-versions) for when to choose which. *** ## Causes & Effects Variable roles fence off the ends of the causal chain: * **Drivers (inputs)** — pure drivers. Only other drivers are allowed to influence them. * **Outcomes (results)** — pure outcomes. They can only send edges to other outcomes. Variables not marked are free to be cause or effect, in either direction. In the example, customerID, InternetService, MultipleLines, and PhoneService are drivers; Churn is an outcome. *** ## Prior Knowledge Encode certainty about specific edges before discovery runs: * **Known relationships** — edges that must exist. Use when you have experimental evidence or domain certainty. * **Blocked relationships** — edges that cannot exist. Use when a connection is logically impossible. Both lists are optional; both improve the resulting graph when you have real prior knowledge to add. *** ## Variable Ordering Constrains causal precedence at the variable level. *"TechSupport must come after InternetService"* tells discovery that TechSupport cannot be a cause of InternetService — only an effect, direct or indirect. Useful when temporal order is known or domain logic is clear. *** ## What happens when you run Click **Modify model**, change what you need in the builder, and run. A new version of the twin is created and trained against the updated configuration. The kind of change decides the version number: * **Major** (1.0.0 → 2.0.0) — the data changed: a different Dataset, a change in the underlying data itself, or a different set of included fields. * **Minor** (1.0.0 → 1.1.0) — a change to the prior knowledge or the ordering constraints. Changing only the algorithm versions, the training options or the variable roles is a patch, not a minor. * **Patch** (1.0.0 → 1.0.1) — any **Retrain model** run, including one where you edited the graph by hand, and any run that changed neither the data nor the prior knowledge and ordering. A **Re-discover & train** run with an unchanged configuration is a patch too. *** ## Other Working with a Digital Twin pages * [Exploring the Causal Model](/more-details/digital-twin/exploring-causal-model.md) — graph layouts and variable details. * [Reviewing Model Quality](/more-details/digital-twin/model-quality.md) — predictive accuracy and per-variable metrics. * [Inspecting Causal Relationships](/more-details/digital-twin/causal-relationships.md) — individual edges and their statistics. * [Version History](/more-details/digital-twin/version-history.md) — multiple versions of the same twin. See [Digital Twin overview](/more-details/digital-twin.md) — general overview.