> For the complete documentation index, see [llms.txt](https://docs.neurolabai.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.neurolabai.io/engineering-and-scientific-assurance/release-state-and-validation.md).

# Release State and Validation

Neurolab separates product availability, predictive-model identity, facts-and-evidence identity, and validation strength. These are related, but they are not interchangeable.

## Public status vocabulary

| State                 | Meaning                                                                                                     |
| --------------------- | ----------------------------------------------------------------------------------------------------------- |
| **Available in beta** | The capability is usable in the beta, subject to access and normal release variation.                       |
| **Conditional beta**  | The capability is usable for exploration but has important route, applicability, or validation constraints. |
| **In development**    | The capability is part of the active product direction but is not a generally available promise.            |
| **Planned**           | The product direction is public, while implementation and final behavior may change.                        |

## Current scientific release state

* The known-compound predictor remains the **v43.262 DE-LEAK B0** three-seed ensemble.
* **v44.16** is the latest candidate facts-and-evidence package, advancing governed records, provenance, evidence coverage, and receptor context without claiming a new predictive checkpoint. It should be treated as active only when a served report or release announcement identifies it that way.
* Known-compound and structure-first routes retain separate validation boundaries.
* Brain-related channels remain method-labeled and must not be fused into one confidence or activation claim.

## Validation principles

Neurolab's release checks are designed to preserve:

* checkpoint and graph compatibility;
* stable report and head contracts;
* explicit route, release, and provenance identities;
* conservative relation direction and evidence state;
* failure when required provenance cannot be resolved; and
* numerical equivalence when a change is presentation-only.

Passing a software or data integrity check does not establish biological correctness or clinical validity. Scientific performance claims remain tied to the exact task, cohort, metric, and limitations described in [Evaluation Methods](/engineering-and-scientific-assurance/evaluation-methods.md).

## Historical examples

The Donepezil, Ketamine, and Modafinil screenshots and fixtures in this guide are frozen historical examples. Their returned values remain useful for learning the interpretation workflow, while current navigation, supporting facts, and feature availability can evolve.

Next: [Limitations and Known Gaps](broken://pages/5NlHxyDS31YmkP5FSGPY)


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.neurolabai.io/engineering-and-scientific-assurance/release-state-and-validation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.