Automated README summary
Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Masroufi imports bank statement exports for Gaza households, cleans transaction notes, resolves vendors, categorises spending, and asks the household only about low-confidence cases. It also includes kitchen planning, pantry, and price-tracking features.
How it uses Jev
One Jev request per unique normalised note asks three typed questions: category (Choice over the taxonomy), is_merchant (Noul), and reducibility (Score). The Choice confidence drives the review queue: below CONFIDENCE_THRESHOLD the transaction is queued for the household instead of auto-categorised. Decisions are cached by normalised note.
Primitives:choicenoulscore
Technique worth stealing
Use the calibrated confidence on a Choice to route only uncertain cases to a human, and cache decisions by normalised input.
Try it
Import data/sample_statement.csv via POST /api/import; default CLASSIFIER_BACKEND=mock needs no key. Run pytest.
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 projectunclear0.47
- Shows a System One patternunclear0.50
- Describes handling uncertaintyunclear0.44
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.84
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelnot found in the excerpt0.17
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 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 24 Oct 2026.