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
An end-to-end quantitative research platform for US equities: data ingestion, pandas technical indicators, LLM-assisted fundamentals, typed AI decisions, a custom backtest engine with walk-forward validation, and scheduled AWS paper trading on Alpaca.
How it uses Jev
Jev (TypeSafe AI) returns typed, probabilistic answers (probabilities, scores, choices) instead of free text, used per ticker and per rebalance date on technical features (data ≤ t-1) and an OpenAI summary of fundamentals. Every paid call goes through a deterministic disk cache.
Primitives:choicescorenoul
Technique worth stealing
Treat look-ahead bias as a bug class: decisions see only data up to the previous close, fundamentals filtered by publication date, orders fill at next open.
Try it
uv pip install -r requirements.txt -e . then python -m jevbt backtest --strategy trend --direction long
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 projectunclear0.43
- Shows a System One patternunclear0.55
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.68
- Top-10 learning shortlist signalunclear0.43
- Is a replica of the modelnot found in the excerpt0.11
- Solves a common problem (0–2)score on a 0–2 scale0.98 / 2
- About JevFound in material0.96
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.