Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A rerunnable test suite probing how TypeSafe Jev and Cloudflare Clef decision models respond to state poisoning, prompt injection, truncation, and guard questions, using a synthetic citation-checker knowledge base.
How it uses Jev
Jev answers typed questions (noul yes/no probability, choice among options) over a state containing claims and a synthetic KB. Experiments edit, prepend, or append text to the state and record whether verdicts flip, e.g. a fake empty STATE: header making true claims return says_nothing.
Primitives:choicenoul
Technique worth stealing
Appending a fake empty STATE: header after evidence makes Jev answer says_nothing for true claims when questions say 'the state'.
Try it
npm install; set env keys; npx tsx experiments/01-truncation.ts --backend jev
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 projectunclear0.46
- Shows a System One patternnot found in the excerpt0.17
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersunclear0.49
- Is a runnable toolnot found in the excerpt0.07
- Top-10 learning shortlist signalnot found in the excerpt0.24
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.32 / 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 20 Oct 2026.