> For the complete documentation index, see [llms.txt](https://docs.uprightplatform.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uprightplatform.com/methodology/net-impact/overview-of-the-upright-net-impact-model/product-model-research-preview.md).

# Product model (research preview)

{% hint style="info" %}
This page describes Upright's research preview methodology for producing net impact data. For information on the classic product model. see [this page](/methodology/net-impact/overview-of-the-upright-net-impact-model/product-model-classic.md)[.](/metrics/net-impact.md)
{% endhint %}

### Inputs

The main inputs for the product model include:

* **Research papers** found relevant by the teacher model when teaching the specialized model (discussed below)
* **Base model weights** (current base model is [Ministral 3](https://docs.mistral.ai/models/ministral-3-14b-25-12)), which are distilled from usual data sources used to train Large Language Models.

### Algorithm

Conceptually, the product-level impact size estimates are produced in three phases: 

1. Training a specialized model for high-performance impact size inference
2. Using the specialized model to pairwise compare the sizes of millions of impacts (thousands per product)
3. Running a solver to derive coherent implied impact sizes estimates from the pairwise comparison results

The impacts to be sized are defined in Upright's universal impact structure, a hierarchical list of around \~800 impact topics across Environment, Society, Knowledge, and Health.

The training and motivation for the approach is further discussed in [this blog post](https://www.uprightproject.com/blog/leena-2/).