A candidate-scoring head returns distributions for gates, routes and scores without decoding prose or JSON answers. The README compares a benchmark-trained AgentJev specialist with Jev 1.13.0 evaluated zero-shot; these use different training conditions.
jev_stock: An experimental JEV-powered framework for forecasting
sosopop/jev_stock
VerifiedResearchDocumented
jev_stock: An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data. See Jev references and source code.
Repository description: An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
What you can build with it
Get started
Clone the repository and follow its README for install and usage. JevHunt has not run this project.
git clone https://github.com/sosopop/jev_stock.gitProject facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- Not reported; check the repository
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-17
- Last code update
- 2026-09-17
- GitHub stars
- 15
- Evidence checked
- Sep 29, 2026
- Metadata checked
- Sep 29, 2026
- Check status
- Up to date
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
The current adapter sends a JSON payload with three parts: `model`, `state`, and `questions`. The source currently selects `jev-latest` and posts to TypeSafe's System One endpoint. Each question is a `choice` question with exactly three allowed outcomes. The response parser accepts only those outcomes and requires finite probabilities for `up`, `flat`, and `down` whose sum is close to one.
Evidence commit: 81fa919795084ba942632d35c9986a1ece7162f9
Discovered through: awesome-jev.
How we review →Suggest a correction · Claim this listing · Submit a project