Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python benchmark that tests TypeSafe's Jev (System One model) on real IMDB movie reviews with known labels, measuring accuracy, latency, cost, and confidence calibration for sentiment, spoiler detection, and quality scoring.
How it uses Jev
Each review is sent to Jev in a single system_one() call with three typed questions: Choice for sentiment (positive/negative/mixed), Noul for is_spoiler (boolean probability), and Score for quality (1-3 scale). Results are saved to results/ with per-review breakdown.
Primitives:choicenoulscore
Technique worth stealing
Combining multiple typed questions in one system_one() call to get calibrated probabilities for sentiment, spoilers, and quality simultaneously.
Try it
git clone, add TYPESAFE_API_KEY to .env, then uv run python main.py -n 5000
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 projectFound in material0.91
- Shows a System One patternnot found in the excerpt0.11
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersFound in material0.98
- Is a runnable toolnot found in the excerpt0.07
- Top-10 learning shortlist signalnot found in the excerpt0.33
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale0.62 / 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 3 Oct 2026.