Double-checking citations
Official TypeSafe cookbook example for checking whether source context actually supports a claim.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This recipe in TypeSafe's Jev documentation shows how to double-check citations. According to the list summary, it is an official example of asking whether a piece of source context supports a given claim.
The pattern is useful for RAG systems, research assistants and report generators: after an LLM writes a claim with a citation, a cheap yes/no judgment checks the claim against the cited text, and unsupported claims can be flagged or removed.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this source context support the claim?(inferred) | yes · no |
How it works
- Pair each claim with its cited source text
- Ask Jev whether the source supports the claim
- Flag or drop unsupported claims
Strengths
- Cheap per-claim verification
- Official, documented pattern
Caveats
- List-only entry; recipe not reviewed
Getting started
See https://docs.typesafe.ai/cookbooks/citation_check.At a glance
- Type
- Article
- Status
- production
- Has code
- yes
Use cases and integrations
How curated lists describe it
Official example of checking whether source context supports a claim.
cobanov/awesome-jev
Frequently asked questions
What does the recipe check?
Whether source context supports a claim.
Where would I use it?
After generating cited answers in RAG or research tools.
Who publishes it?
TypeSafe, in the official docs.
Related projects
Published Jev client and claim check from the Fake/Real evidence-review site, where Jev filters sources and judges each claim.
ProjectproductionTypeScriptSmall Python demos of Jev: parallel Noul ticket checks with measured speedup, and a three-way Choice citation and claim checker.
AppprototypePythonEducational code where a local LLM voices a game NPC and Jev classifies player messages and checks every line for spoilers.
ProjectprototypePythonTypeScript demos for testers: Jev triages CI test failures, gates test-agent commands and RAG answers, across gateway, Ollama and Foundry.
LibraryprototypeTypeScriptChecks whether each cited paper supports its citing sentence: code fetches papers, Claude proves a quote, Jev scores it, a human decides.
ServiceproductionLearning lab for DeepEval with Jev as the judge: replayed evaluations, adjustable decision rules, release gates and drift alerts.
ProjectprototypePython