Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local Python CLI that screens research abstracts against a research-interest text using OpenAI Decisions, TypeSafe JEV, or both, with resumable scoring, cost accounting, CSV/JSONL exports, comparison metrics, and an offline HTML explorer.
How it uses Jev
JEV is one of two selectable scoring providers (--provider jev or both). It scores abstracts against the research interest; in both mode its scores are kept independent and compared with OpenAI for agreement, disagreement, and discordant views.
Primitives:score
Technique worth stealing
Run two independent scoring providers and preserve their separate scores so agreement and disagreement can be compared rather than merged.
Try it
uv sync, set JEV_API_KEY in .env, then uv run abstract-sift score --corpus demo --query-file examples/interest.txt --provider jev
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 projectnot found in the excerpt0.06
- Shows a System One patternunclear0.41
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.99
- Is a runnable toolFound in material0.90
- Top-10 learning shortlist signalnot found in the excerpt0.12
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 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 29 Oct 2026.