# Adaptive Classifier: Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/adaptive-classifier
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model · Text classification

### [typed-decisions-minilm-l6-specialist](https://savrn.com/models/typed-decisions-minilm-l6-specialist)

[Adaptive Classifier](https://savrn.com/model-publishers/adaptive-classifier)

A specialist for the Typed Decisions (workflow, question) on a frozen sentence-transformers/all-MiniLM-L6-v2 encoder, 20 heads in total. Each head takes the rendered state, the question text and its options, and returns a probability distribution over the question's labels. This is not zero-shot. It was fitted on the 1,200-case train split of Typed Decisions and is scored on the 400-case test split. Per the benchmark's own rules it is a specialist, and should not be compared with generalist models that answer unseen question schemas. "This run" is the model in this repository, fitted and scored from the public dataset with adaptive-classifier 0.2.0 on Apple MPS, and scored by the benchmark…

Open weights apache-2.0 adaptive-classifier

[View model](https://savrn.com/models/typed-decisions-minilm-l6-specialist)

## Datasets

Dataset · Text classification

### [ai-detector-data](https://savrn.com/datasets/ai-detector-data)

[Adaptive Classifier](https://savrn.com/model-publishers/adaptive-classifier)

A continuously-growing collection of AI text detection predictions with optional user feedback, generated from the AI Text Detector Space. Every time someone analyzes text or a URL on the Space, the prediction is appended to this dataset. Users can also click "Correct" or "Incorrect" to provide feedback, which gets stored alongside the prediction. Or with the datasets library: 1. Model evaluation — see how the detector performs on real-world text submitted by users 2. Retraining data — records with feedback provide ground-truth labels for continuous learning 3. Failure analysis — examine where the model is wrong (feedback == "incorrect") 4. Distribution analysis — what kinds of text/URLs…

Publicly accessible apache-2.0 n<1K

[View dataset](https://savrn.com/datasets/ai-detector-data)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-09-23.
- [Hugging Face profile](https://huggingface.co/adaptive-classifier)
- [How the hub is built](https://savrn.com/model-hub/methodology)