Automated README summary
Automatically summarized from the README on 7 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A proof of concept that evaluates fraud risk in SAP S/4HANA purchase orders. ABAP calculates risk indicators from order, supplier, and buyer data; a Fiori Elements app sends anonymous indicators to Jev for typed decisions, and ABAP classifies orders as release, approval, or block in shadow mode.
How it uses Jev
Jev answers seven typed questions on anonymous indicators: five noul questions (fornecedor_ficticio, desvio_pagamento, sobrepreco, fracionamento, fraude_interna), one score (atipicidade 1–5), and one choice (acao). ABAP receives probabilities, applies thresholds, and classifies the order; no order is blocked in shadow mode.
Primitives:noulscorechoice
Technique worth stealing
Shadow mode: log Jev evaluations without blocking orders, enabling safe calibration.
Try it
cd app && npm install && cp .env.example .env && npm start
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 material0.92
- Shows a System One patternFound in material0.88
- Describes handling uncertaintynot found in the excerpt0.24
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolunclear0.56
- Top-10 learning shortlist signalunclear0.49
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.90 / 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 7 Oct 2026.