> ## Documentation Index
> Fetch the complete documentation index at: https://docs.graphify.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Formal verification
> Compare changed functions, inspect behavioral differences, and understand each verification verdict.
Graphify Cloud includes **Formal Verification** as a core feature. It compares changed functions with their earlier implementations to determine whether behavior is preserved or whether a concrete input produces a different result.
Open **Formal Verification** in [Graphify Cloud](https://app.graphify.com). Hosted plans include verification with different usage and concurrency allowances; see [current plans](https://graphify.com/pricing).
## Inspect a verification run
Use the **Repository** filter or select **All repositories** to see workspace runs.
Check the pull request and commit, then expand the run to inspect its outcome and per-function results. A finished run can contain a mixture of outcomes.
Inspect the source file, function, and verdict. For a behavior change, the detail can include the distinguishing input and the old and new values. An abstention or failure includes its reason when available.
Use **Open pull request** or the commit link to investigate the implementation. When a run has finished, **Re-run verification** can queue another attempt; queued and running attempts cannot be rerun simultaneously.
## Understand the result
| Result | What it means |
| --------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| **Proved equivalent (bounded)** / `equivalent` | The proof method established equivalence within its supported model or analysis bounds. |
| **Behavior change** / `distinguished` | An input distinguishes the implementations. Inspect whether the witness was reproduced in the sandbox or remains unconfirmed. |
| **No divergence sampled (not proven)** / `may_equivalent` | The exercised inputs showed no difference. This is empirical evidence, not a proof. |
| **Abstained** / `unsupported` | The method could not analyze the function within its supported domain or budget. |
| **Errored** / `error` | Verification failed to produce a valid result for the function. |
**Completed** describes a run's lifecycle; it does not mean every function was proved equivalent. Queued, verifying, failed, cancelled, skipped, and expired runs also retain their own status. A run that verified no functions does not imply the change passed.
## Configure and use verification
Repository controls include a **Formal verification** setting for pull requests. Use [Repositories and builds](/platform/repositories) to check repository configuration and indexing before investigating missing runs.
When Graphify supplies a distinguishing input, use it to reproduce the difference and create a regression test. Review whether the changed behavior was intentional before deciding what to change.
[Learning](/platform/learning) tunes advisory review feedback only. It cannot change proof verdicts or hide a witness from the verifier.
## Scope of a proof
Verification is function-level and differential: the previous implementation is the reference. It does not establish that the application meets its intended requirements. Read bounds, unsupported cases, and reproduction status with the result.
For the separately installed enterprise CLI, the website's [verification reference](https://graphify.com/docs/verification) documents `verify-edit` and gate configuration. Those commands are distinct from the hosted console workflow and the public open-source CLI.