Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An open laboratory testing whether fast, formal railway dispatching decisions suit typed-output decision models like Jev, comparing them against generative LLMs, LLM-written MILP, classical OR and rule baselines in the Flatland simulator.
How it uses Jev
Jev is one of several contestant engines in the dispatch controller. It receives the same decision card as every other engine and selects among safe options prepared by code. The README does not specify which Jev primitives are used or how its probabilities are consumed.
Technique worth stealing
Code computes, the model selects: a deadlock-avoidance interlocking guarantees safety, engines only choose among safe options.
Try it
pip install -e ".[dev]"; pytest; add TYPESAFE_API_KEY / DEEPSEEK_API_KEY for live engines.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectunclear0.40
- Shows a System One patternnot found in the excerpt0.39
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolnot found in the excerpt0.08
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelnot found in the excerpt0.11
- Solves a common problem (0–2)score on a 0–2 scale0.82 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 6 Oct 2026.