> 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 creates a new version and retrains, leaving the current one untouched. 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, showing the Data View, 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.

*** ## Data View The dataset the twin is built from. 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 Data View, 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; toggle each field to include or exclude. 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) and **CausalACO** (metaheuristic structure learning) are 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. *** ## Variable Roles Variable Roles fence off the ends of the causal chain: * **Sources (exogenous)** — pure drivers. Only other sources are allowed to influence them. * **Targets (outcomes)** — pure outcomes. They can only send edges to other targets. Variables not marked are free to be cause or effect, in either direction. In the example, customerID, InternetService, MultipleLines, and PhoneService are sources; Churn is the target. *** ## 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 Data View, a change in the underlying data itself, or a different set of included fields. * **Minor** (1.0.0 → 1.1.0) — a configuration-only change (algorithm versions, training options, variable roles, prior knowledge, or ordering constraints) — or any **Re-discover & train** run, which starts a fresh discovery pass and advances the minor version even with an unchanged configuration. * **Patch** (1.0.0 → 1.0.1) — a plain **Retrain model** of the existing graph with no changes at all. *** ## 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.