Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A calibre plugin that suggests subject and genre tags for books using TypeSafe AI JEV. It preserves existing tags and lets users review suggestions before applying them, for single books, selected books, or entire libraries.
How it uses Jev
Jev evaluates each configured tag category independently, along with a check for sufficient evidence. It takes book metadata (title, authors, description, language, series) and optionally EPUB excerpts as state, and returns probabilities for each category. Results are used to suggest tags, with thresholds determining automatic readiness.
Primitives:choicescore
Technique worth stealing
Using per-category thresholds and a closeness margin to decide when suggestions are confident enough for automatic application.
Try it
Install the plugin ZIP in calibre, enter your TypeSafe AI API key in settings, and use Classify current book, selected books, or entire library.
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 material0.71
- Shows a System One patternnot found in the excerpt0.27
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 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 1 Oct 2026.