Automated README summary
Automatically summarized from the README on 27 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local tool that captures a Meta advertiser's active ads from the Ad Library, classifies each creative with the Jev (TypeSafe) model, and shows in a browser dashboard which patterns appear among ads that stay live longest.
How it uses Jev
Jev classifies each creative across seven dimensions (format, hook, angle, offer, proof, objection, call to action) using the image and text via a native endpoint, in batches, with single-choice questions. Confidence and full probability distributions are stored as returned; confidence below 0.65, missing visual evidence, or text-only classification flags the item for review.
Primitives:choice
Technique worth stealing
Reserving a fixed input-token budget before each paid call, replacing it with API-reported usage, and halting scheduling on unreliable usage.
Try it
Run `scripts/lab.py serve`, open http://127.0.0.1:5194, enter a page ID, then capture and classify.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.85
- Shows a System One patternnot found in the excerpt0.09
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelnot found in the excerpt0.29
- Solves a common problem (0–2)score on a 0–2 scale0.93 / 2
- About JevFound in material0.99
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 27 Oct 2026.