> For the complete documentation index, see [llms.txt](https://docs.tracr.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tracr.com/tracr-articles/tracr-rough-check.md). # Tracr Rough Check Read this article to learn more about Tracr Rough Check. ## You need to know * Rough Check determines whether there is a match between a scan of a rough diamond uploaded by a producer and a scan of a rough diamond a manufacturer uploads to Tracr. * Rough Check matching is performed using Diamond ID, a core service in the Tracr platform ecosystem primarily tasked with validating, verifying, and identifying diamonds. * The results of a Rough Check appear in the Tracr Inventory and the Diamond Details page and in data about a diamond returned using the Tracr API once the diamond is polished and unlocked. * A successful Rough Check is mandatory to be able to split and polish a rough diamond over 2cts. * Rough Check status is carried downstream from the original rough diamond to later diamond lifecycle states. ## What is Rough Check? Rough Check provides additional confidence in the provenance of a diamond recorded on the Tracr platform. The Rough Check process uses Diamond ID to evaluate whether the information about a rough diamond recorded by one party (for example, a manufacturer) matches, within a given tolerance, a rough diamond recorded by another party (for example, a producer). ## Where do the results of Rough Check appear? You will be able to see a Rough Check against a diamond in your Inventory once a diamond is polished and unlocked. Prior to the diamond being polished and unlocked Rough Check will be shown as `Restricted` in the inventory, and `false` in the API. Once the diamond is polished and unlocked the outcome of Rough Check will be available. ### Inventory All Tracr inventory screens display a **Rough Check** column. #### Rough and Split Inventory For rough which don't yet have a scan `Missing Scan` is displayed. Once a scan is uploaded the rough check process is performed, the outcome of which is `Restricted`. #### Polished Inventory Once the diamond is polished and unlocked the Rough Check value is displayed. A green tick in the **Rough Check** column indicates that a scan was uploaded to Tracr by the manufacturer with the diamond, which Tracr has checked and matched against the producer's scan of that diamond before it was transferred to the manufacturer. Rough Check status is carried downstream from the original rough diamond to later diamond lifecycle states. The following example shows a Rough Check against two diamonds in the Polished Inventory. The other diamonds have not been matched.

Rough Check in the polished inventory.

### Diamond Details The Diamond Details page also shows the result of a Rough Check for diamonds which are polished and unlocked. Open the Diamond Details page for a diamond and scroll down to the **Rough** section.

Rough Check in the Diamond Experience.

A green tick next to **Rough Check** indicates a match between a manufacturer’s and producer’s scan of that diamond. Rough and split diamonds will always show `Restricted` as the **Rough Check** value. Note that if a rough diamond is matched, then split, then polished and transferred, the Rough Check mark appears at every point in the chain, in the **Rough** lifecycle state section of the Diamond Details page. ### Tracr API Rough Check status is exposed as a `rough_check` field in PCS-API. Pass the Tracr Diamond ID to the `/diamonds` endpoint to return data about a diamond. The `rough_check` field in the response indicates whether that rough diamond has been verified by Tracr Rough Check. Prior to the diamond being polished and unlocked the `rough_check` field will show `false` regardless of the Rough Check state. ## How does Rough Check work? Rough Check uses advanced Machine Learning algorithms to understand features and accurately identify and compare diamond characteristics between a rough diamond received by a manufacturer and a rough diamond recorded by a producer. Central to this process is a detailed scan of the surface of each diamond, which provides a unique digital fingerprint. Rough stone matching primarily consists of the following sequence: {% stepper %} {% step %} ### Filtering by producer batch/lot/box number This provides a set of diamonds to be matched against the manufacturer’s diamond. Where more than one diamond is provided, the algorithm searches the available diamonds to find the best match. {% endstep %} {% step %} ### Filtering by weight and structural features Carat measurement errors can occur due to inconsistency between participant scanning machines or other factors such as machine calibration and location, and the algorithm adaptively targets stones within specific ranges to further reduce the search set. {% endstep %} {% step %} ### Surface alignment checks A surface alignment check determines how well two scans overlap geometrically, providing a clear measure of similarity. Usually, if the scans are generated with high-accuracy machines then a much better alignment is observed. {% endstep %} {% endstepper %} ## What is required to get a Rough Check? Rough Check matching requires 3D scans of diamonds uploaded when a producer and manufacturer register diamonds on Tracr. Tracr requires high-quality scans that are sufficiently detailed to allow matching and identification. Where a match is found within a given tolerance, the Rough Check is shown. {% hint style="warning" %} Important: To ensure sufficient scan quality for accurate matching, scans must be uniform and have at least 6000 vertices. {% endhint %} Note that Tracr cannot always guarantee a match when the data provided by participants is suboptimal. Factors such as significant weight discrepancies, physical alterations before scanning, or low-quality 3D scans can reduce confidence in a match, leading the match to fail. One of the key metrics for assessing matching success is the matching rate, which represents the number of diamonds successfully identified compared to the total number provided. While Tracr will accept licensed 3D scans in standard formats from any scanner meeting Tracr’s minimum requirements, different types of scanners and their settings can affect the matching rate, and every stone, box or shipment has its own particularities. --- # 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.tracr.com/tracr-articles/tracr-rough-check.md?ask=&goal= ``` `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.