# Mapika/decider

> A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model class built on Qwen3.5-2B.

- Magnitude: 1.1 out of 10 — Steady
- Stars: 1,150 total · +1 star measured 2026-10-16, 00:14–03:02 UTC, ≈ 7 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-16 · Last push: 2026-10-12
- GitHub: https://github.com/Mapika/decider · Page: https://gitnova.dev/en/r/Mapika/decider

## Useful for

- Route support tickets to departments with confidence scores
- Build confidence-gated routing that escalates uncertain cases to humans
- Score customer frustration level from ticket text

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:14–03:02: 1149 → 1150 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +7 stars, using observed gains and the previous day.
- The repository is 30 days old and already has 1,150 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 51
- Issues and pull requests: 21
- Watchers: 3
- Average over the last week: 6 per day
- Usual pace: 33 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 14, 20, 8, 11, 6, 5, 10, 4, 7, 5, 3, 7, 0, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-03 1.4, 10-04 1.3, 10-05 1.7, 10-06 1.7, 10-07 1.4, 10-08 1.5, 10-09 1.2, 10-10 1.4, 10-11 1.5, 10-12 1.2, 10-13 1.3, 10-14 1.1, 10-15 1.0, 10-16 1.2

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-16 03:06 UTC, updated every 30 minutes.