Automated README summary
Automatically summarized from the README on 30 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A notebook comparing Jev, TypeSafe AI's hosted decision model, against open decoders, encoders and specialised tools on five document-pipeline chores — language detection, orientation, RVL-CDIP classification, bundle splitting and parse-tier triage — using liteparse for all PDF work.
How it uses Jev
Jev answers each chore as a typed Choice question over state built from OCR text or liteparse complexity signals: Choice(12) for language, Choice(4) for orientation, Choice(16) for RVL-CDIP class, Choice(2) per page boundary for bundle splitting, and Choice(2) for parse-tier triage. The notebook drives Jev via JevBackend and compares its answers to open baselines.
Primitives:choice
Technique worth stealing
Frame each pipeline chore as a typed Choice question over OCR text or complexity signals, then compare against open baselines.
Try it
uv sync; add TYPESAFE_API_KEY; uv run build-corpus all; uv run modal deploy modal_app.py; uv run jupyter lab jev_vs_open.ipynb
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 projectunclear0.49
- Shows a System One patternunclear0.58
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.12
- Is a runnable toolnot found in the excerpt0.11
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.28 / 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 30 Sept 2026.