# LiQiiiii/Jeva

> Jeva is a natively designed System One model: given a state and typed questions it returns candidate probabilities, a Boolean probability, or an expected rubric score. A language encoder represents the state and each option independently, while decisions stay set-dependent.

- Magnitude: 2.2 out of 10 — Early signal
- Stars: 101 total · +13 stars measured 2026-10-18, 00:28–11:49 UTC, ≈ 23 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-10-12 · Last push: 2026-10-17
- GitHub: https://github.com/LiQiiiii/Jeva · Homepage: https://arxiv.org/abs/2610.18773v1 · Page: https://gitnova.dev/en/r/LiQiiiii/Jeva

## Useful for

- Route support tickets to teams with per-candidate probabilities
- Estimate the probability that a report describes an ongoing outage
- Assign an expected impact score using a supplied rubric

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 00:28–11:49: 88 → 101 stars (+13). This is the change over that interval.
- Estimated end-of-day forecast: about +23 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 101 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.

## 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: 5
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 17 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-12 … 2026-10-18: 0, 9, 65, 2, 6, 14, 13

## Magnitude by day, last 2 days

10-17 1.2, 10-18 2.2

## Similar by description

1. **mizorewww/laya-mlx** — 1.2 · Steady · Language models · Python · +4 stars measured 2026-10-18, 00:28–11:52 UTC, ≈ 7 by evening
   Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-mlx.md
2. **bespokelabsai/nimble** — 0.9 · Steady · Language models · Python · +3 stars measured 2026-10-18, 00:28–11:53 UTC, ≈ 5 by evening
   Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition checks, and policy…
   Full card: https://gitnova.dev/en/r/bespokelabsai/nimble.md
3. **NandhaKishorM/vegaml** — 2.0 · Steady · Language models · Python · +11 stars measured 2026-10-18, 00:26–11:50 UTC, ≈ 20 by evening
   Library for typed decisions from a frozen language model and a small physics engine: returns a choice, score, or probability with calibration, conformal sets, and an abstain flag. Supports 73k context and images, runs locally.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/vegaml.md
4. **firelex/jeff** — 0.6 · Steady · Language models · Python · +1 star measured 2026-10-18, 00:29–11:54 UTC, ≈ 2 by evening
   Small fine-tuned Qwen3.5 and Gemma 4 models for zero-shot classification: given a situation description and a list of options, they return a calibrated probability for each option in a single forward pass.
   Full card: https://gitnova.dev/en/r/firelex/jeff.md
5. **kouhxp/gutsy** — 0.1 · Steady · Language models · HTML · +0 stars measured 2026-10-18, 00:30–11:54 UTC, ≈ 0 by evening
   Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. Runs on CPU via GGUF, Jev-style API.
   Full card: https://gitnova.dev/en/r/kouhxp/gutsy.md

---

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 2026-10-18 11:55 UTC, updated every 30 minutes.