Skip to content
JevDirectory.orgTraffic count unavailable. View site traffic
CommunityJev Practices & Patterns

Jev Synergy Screening

Screens MEDLINE titles and abstracts for an ADHD systematic review with Jev, scored against the Cohen 2006 Abstract Triage gold labels, with a published rule rather than a bare model verdict.

See highlightsOpen github.com
Stars
2
Language
Python
Published by
Community
Author
PistachioAIHQ
Last verified
Oct 2026

PistachioAIHQ/jev-synergy-screening

Organization repository on GitHub

View on GitHub

Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels

Forks
1
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Viral life-sciences demo: screen MEDLINE title + abstract as include vs exclude with TypeSafe Jev (System One), compared to Abstract Triage gold from Cohen et al. 2006. Gold story = Abstract Triage (TIAB) only — not Article Triage, not MEDLINE PT, not SYNERGY. Optional mode: Bat4RCT r3ship (MEDLINE PT RCT tagging) remains in the UI toggle. Custom open data from the authors’ page — not CC-BY. Cite Cohen 2006 (see data/COHENLICENSENOTE.md).

Quoted from the project's README. Read the full README.

Tagscommunityjevbestcatalog-importawesomejev
Works forJev for Classification
Used inJev for Software & DevTools
Languages
Python

Highlights

  • Gold is Cohen's Abstract Triage status on title and abstract only; Article Triage, MEDLINE PT and SYNERGY labels are explicitly unused.
  • A Jev include/exclude choice is combined in code with atomic gates for population, drug, outcome, study design, publication type and duration.
  • On the full 851-abstract set it reports 94.6% accuracy and 75.3% F1 at roughly $0.078, and labels the 200-item film grid as a subsample.
  • A local demo server exposes the rule in a questions drawer plus cached replay and the metrics endpoints behind the same run.

Watch out

The repository name says SYNERGY, and the README goes out of its way to say the gold labels are not: gold is Cohen's Abstract Triage status, and the SYNERGY included label is on the never-used list. The head-to-head grid is a stratified hundred-abstract run with only ten positives, and the README itself says not to headline it; the full-set result is the number to read, where the include class is about 9.9%, so accuracy sits near 94.6% while F1 is 75.3% with 32 false positives. Precision is the honest headline for a screening task, and 57.1% on the film grid means substantial manual reading remains. The Anthropic comparison used a structured include or exclude tool with no chain-of-thought essay, which is a protocol choice worth knowing before reading the cost gap. Data comes from the authors' page and is not CC-BY. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

jev-on-a-laptop
24GitHub stars
Unofficial laptop study of parallel constrained decoding: prefill once, share the KV cache across fields, and decide all schema fields in one batched forward pass without writing JSON.
Jev Practices & Patterns#community#jevbest#catalog-import
Communityrorshopping/jev-on-a-laptopPython
jeval
22GitHub stars
Offline evaluator that checks whether classifier confidences match reality and converts mistake costs into a deployable threshold, emitting an HTML report plus machine-readable threshold files.
Jev Practices & Patterns#community#jevbest#catalog-import
Communityrlaope/jevalPython
jev-rag-benchmark
16GitHub stars
Vendor-neutral harness that tests whether Jev reranking improves a small RAG stack, using frozen hybrid BM25 plus BGE-M3 candidates and isolating retrieval, rerank, and generation stages.
Jev Practices & Patterns#community#jevbest#catalog-import
Communityerendikmenn/jev-rag-benchmarkPython
system-one
37GitHub stars
Minimal Python recipe that turns any causal LLM into a Jev-style classifier by prefilling choice_index and constraining sampling to legal indexes in one forward pass.
Jev Practices & Patterns#community#jevbest#catalog-import
Communitysgoedecke/system-onePython
system-one-open
39GitHub stars
Open replica of the typed decision API on openly available base models, answering choice, score, and true-probability questions in one forward pass with no decoding.
Jev Practices & Patterns#community#jevbest#catalog-import
Communitymithalouni/system-one-openPython
Jev_apps
34GitHub stars
Curated catalog of community Jev applications grouped by use, where each case explains the mechanism and states what the public evidence does and does not prove.
Jev Practices & Patterns#community#jevbest#catalog-import
CommunityJackZeng/Jev_appsPython

From the Jev guides

Original write-ups on what this entry is for.

Designing the State: What to Include and What to Drop
Most Jev accuracy problems are state problems. What belongs in a state, what is a pre-made judgment to leave out, and why naming the slice you ask about matters more than the wording.
Jev Practices & Patterns#state#design#primitives
Read article
Noul, End to End: One Probability and a Dozen Thresholds
A Noul returns one number and no separate confidence. How to read the value, pin its boundary with criteria, split compound questions, and set a per-action threshold that matches the cost of being wrong.
Jev Practices & Patterns#noul#primitives#confidence
Read article
Scoring Without Measuring: Bands, Rubrics, and Composite Triage
A Score is a weighted position, not a ruler. Why the number can land between levels, why levels are judged separately, and how to combine several atomic scores in code instead of one crowded rubric.
Jev Practices & Patterns#score#primitives#scoring
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai