# Corners AI: coco-decision

> A Korean and English decision adapter on Qwen3.5-4B. A state, a typed question and lettered options go in; probabilities are read from the option-letter logits of one forward pass, with no generation. Jev-inspired, trained with a Brier term for calibration.

- Page: https://systemonemodels.ai/corners-ai/coco-decision
- API: https://api.systemonemodels.ai/v1/models/corners-ai/coco-decision
- Download: `pip install systemonemodels && systemone pull corners-ai/coco-decision`

## Facts

| | |
|---|---|
| Maker | Corners AI (https://systemonemodels.ai/corners-ai) |
| Decides | choice, score, noul, classify, route |
| Architecture | coco-decision |
| Base model | qwen/qwen3.5-4b |
| Parameters | 4.0B |
| Context | 4K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-29 |
| Latest version | 1.0.0 |

## Reported evaluation

Suite: JevBench public set (231 items), the maker's run with omj bench in bf16. Numbers are the publisher's own.

- Decision accuracy: 87.0%
- Calibration error (ECE): 0.070

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# CoCo-Decision-4B-Ko

A Korean and English decision adapter on Qwen3.5-4B. A state, a typed question and lettered options go in; probabilities are read from the option-letter logits of one forward pass, with no generation. Jev-inspired, trained with a Brier term for calibration.

A rank-16 LoRA (39 MB) on Qwen3.5-4B, published by Minyoung Yu as Corners AI and built with his oh-my-jev toolkit. It reads option-letter logits, so it is Jev-inspired, like Tev1. Intended for routing and gating in agent systems. The card warns that JevBench numbers may overstate results, because synthetic training data was designed after studying the public task types, and that calibration is weaker than Jev's in its own comparison. Weak on long policy documents (0.63) and date arithmetic (0.40, overconfident). On MASSIVE ko-KR the maker reports 0.915 (ECE 0.023).

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 4B |
| Base model | `Qwen/Qwen3.5-4B` |
| Maker | Corners AI |
| Released | 2026-09-29 |
| License | apache-2.0 |
| Reported accuracy | 87.0% |

## Get the weights

```bash
pip install systemonemodels
systemone pull corners-ai/coco-decision
```

The files are served from the maker's Hugging Face repository, [`corners-ai/CoCo-Decision-4B-Ko`](https://huggingface.co/corners-ai/CoCo-Decision-4B-Ko), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/corners-ai/CoCo-Decision-4B-Ko)
- [oh-my-jev toolkit](https://github.com/iamupd/oh-my-jev)

---

*This page was opened by System One for Corners AI, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models