> 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/version-history.md). # Version History A [Digital Twin](/more-details/digital-twin.md) is not a single fixed model. Every time you train it — on a new Data View, a changed configuration, or a refreshed dataset — RootCause keeps the result as a numbered **version**. Each version bundles a configuration and the model trained from it, so you can compare versions, return to an earlier one, and see how the twin has evolved. One version is **active** at any time: the one your [simulations](/more-details/digital-twin/simulation-types.md) run against. The others stay on record, ready to be reactivated. *** ## The Version History view Open a twin and, from its Overview, follow **Version History**. The panel shows every version of that twin as a tree, with the active version marked, alongside an **All versions** table listing each version's number, status, and creation time.

The Version History panel for a twin: a version tree showing v2.0.0 above v1.0.0, and an All versions table listing v2.0.0 as Active and Trained on 05 May 2026, and v1.0.0 as Failed, with a Use action to switch to it — Version History. The tree shows lineage; the table reports each version's status and offers **Use** to switch the active version.

Each version carries a **status**: * **Active** — the version simulations currently run against. Exactly one version is active. * **Trained** — a completed version, ready to be made active. **Use** switches to it. * **Failed** — training did not complete. The version is kept on record but cannot be used; retrain or delete it. A version mid-training shows its progress in place until it resolves to Trained or Failed. *** ## How versions are numbered Versions follow a **major.minor** scheme, and the kind of change you make decides which number advances: * **Major** version (e.g. 1.0.0 → 2.0.0) — the **Data View** changed. A different underlying dataset is a different model, so it earns a new major number. * **Minor** version (e.g. 1.0.0 → 1.1.0) — anything else: fields included, algorithm versions, variable roles, prior knowledge, or ordering constraints. The Configuration form tells you which kind of version your edit will produce before you commit it — see [Configuration › What happens when you save](/more-details/digital-twin/configuration.md#what-happens-when-you-save). *** ## Creating a new version From a twin's Config panel, click **Create New Version** (or **Edit & Create New Version** to start from the current configuration). This opens the full specification form — the same one used to [create the twin in the first place](/user-guide/creating-digital-twin.md), with every field documented under [Configuration](/more-details/digital-twin/configuration.md): Data View, name, type, fields, training options, algorithm versions, and the optional Advanced Configuration.

The full Create Digital Twin specification screen scrolled top to bottom, showing Data View, Name, Type, Fields, Training Options, Algorithm Versions, and Advanced Configuration sections, with Discover Relationships and Full Training buttons at the foot — The specification form for a new version. The summary line at the foot recaps the configuration before you train.

Two buttons launch the work: * **Discover Relationships** — run causal discovery only, to inspect the graph before committing to a full train. * **Full Training** — discover relationships and train the model end to end. This is the path to a finished, usable version. *** ## Training and the result While a version trains, the twin shows a live **Discovering relationships** banner and a list of processing stages — preparing data, causal discovery, latent confounder modelling, symbolic equation discovery, and building the model. The configuration cannot be edited until training finishes.

A twin mid-training, with a Discovering relationships banner, a Version panel showing v1.0.0 as the initial version, and a Processing Stages list with progress bars reading 0 of 5 stages complete — A version in training. Each stage reports progress; the run can be cancelled.

On success the banner turns to **Model trained & ready**, the version's status becomes Trained (and active if it is the first), and **Run Simulation** is enabled. The Config panel now shows the version's node and relationship counts and a **Create New Version** link to start the next iteration.

A successfully trained twin showing a Model trained and ready banner, a Run Simulation button, the Version panel, the causal graph, a 72.1% model fit Evaluation score, and a Create New Version link — A finished version. The Evaluation score reports how well this version fits the data — see Reviewing Model Quality.

*** ## Seeing every version at a glance The Digital Twin Management list shows each twin with its current **Version**, node and relationship counts, creation time, and a status dot. It is the fastest way to scan what exists across a workspace and spot which versions are active.

A close-up of the Digital Twin Management list with columns Name, Owner, Type, Data View, Version, Nodes, Relationships, Created, and Status, showing three twins at versions 1.0.0, 2.0.0, and 1.0.0, each with a green active status dot — The management list. The Version, Nodes, and Relationships columns make differences between models visible at a glance.

To compare two versions side by side — their graphs, metrics, and relationships — use [Model Comparison](/more-details/digital-twin/model-comparison.md). *** ## 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. * [Configuration](/more-details/digital-twin/configuration.md) — the fields behind every version. See [Digital Twin overview](/more-details/digital-twin.md) — general overview. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.rootcause.ai/more-details/digital-twin/version-history.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.