Citation evidence collection with Jev
A generator produced a claim and a source pointer. Jev answers whether the source supports the claim. Code decides publish, hedge, or strip the citation.
This unofficial page is the evidence collection slice of the citation checking pack. Intent: apply the Jev (TypeSafe System One) decision model to citation checking evidence collection. Primary search language: Citation Jev evidence collection. Confirm patterns on docs.typesafe.ai. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.
Independent angle (cover ≠ clone): Cite vs generate boundary + failure modes. Cover the citation-check intent; do not mirror a citation-check-noul recipe slug.
Citation use-case context
Evidence collection for citation checking happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the claim + source excerpt facts, filter them, then ask snap questions. This slice is where fan-out cost math belongs: batch questions, do not re-send state.
Hub: RAG passage classification. Compare, when the other tool is the real job: citation services.
Evidence Collection inputs
Collect:
- The atomic claim (one sentence)
- The quoted span, not just a URL
- Source id you will show the reader
Never send:
- Asking Jev to invent a URL
- Ten claims in one Noul
- A PDF page image
Shape the payload like this once the gather step finishes:
{
"claim": "Pro plans include a 14-day refund window.",
"source": { "id": "kb-refunds", "quote": "Pro subscribers may request a refund within 14 days of purchase." },
"answer_draft": "Yes — you have two weeks on pro."
}Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
supports |
Noul | Does source.quote support claim? |
contradicts |
Noul | Does the quote contradict the claim? |
sufficient |
Score | How complete is the support (hedge vs publish)? |
One claim × one quote per atomic Noul. Fan-out multiple claim/quote pairs in one request only if each pair is named in instructions. Do not hide five citations in one Score.
Do not treat a Noul of 0.5 as a “medium” citation checking score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty claim + source excerpt, redaction stripped everything, retriever empty), fail closed on showing a public citation next to a customer answer. Do not invent evidence so Jev has something to say. TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For citation checking, treat public_citation as the high bar (showing a public citation next to a customer answer). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy claim + source excerpts. Label supports / partial / contradicts on a frozen claim–quote set. Pin jev-1.13.0 (the versioned id) after you fit thresholds. jev-latest and the marketing line jev-1.13 can move. Log the response model. TypeSafe’s published list price for jev-1.13 is $0.042 per million input tokens (vendor claim — confirm on the models page); output tokens are free on that same page. Unused distractors still bill as input.
Official Python and JavaScript SDKs read TYPESAFE_API_KEY and retry documented 429/529. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.
Pack map
| Slice | Page |
|---|---|
| Graph and primitives | decision workflow |
What may enter state |
input contracts |
| What to gather first | you are here |
| Atomic rules | policy checks |
| Act / review / abstain | confidence thresholds |
| Reviewer payload | human handoff |
| What to persist | audit trail |
| How it breaks | failure modes |
| Labeled replay | evaluation |
| Shadow → canary | production rollout |
FAQ
Should evidence live in the question text?
Put facts in state and point instructions at claim, source.quote. Criteria stay stable so you can replay.
When do I split calls? One claim × one quote per atomic Noul. Fan-out multiple claim/quote pairs in one request only if each pair is named in instructions. Do not hide five citations in one Score.
Where is the rest of the Citation pack? Start with Citation input contracts and Citation decision workflow. Cluster hub: Use cases.
Can Jev write the bibliography? No. It judges support. Formatting and URL fetching stay in code or another tool.
Is this the same as RAG passage relevance? Related but not the same intent. Relevance is “can this passage help?” Citation is “does this quote support this claim?”
What this page does not claim
- Not a plagiarism checker or fact API.
- No invented support accuracy.
- Not official TypeSafe.
- Official TypeSafe status, or that jev.pro issues API keys.
- That a schema-constrained answer is automatically factually correct.
Disclaimer
This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai.
Primary documentation: https://docs.typesafe.ai. Hub: Use cases.
Sources
Public TypeSafe or adjacent documentation only. No private claims.