Citation audit trail 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 audit trail slice of the citation checking pack. Intent: apply the Jev (TypeSafe System One) decision model to citation checking audit trail. Primary search language: Citation Jev audit trail. 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.
Persist claim text, quote hash, and publish vs strip. Passage keep/drop logs belong to the RAG pack, not here.
Citation use-case context
An audit trail for citation checking is a decision trace: replayable inputs, typed answers, floors, and the action the citation checker took. It is not a chat log and not a clone of a SIEM product page.
Hub: RAG passage classification. Compare, when the other tool is the real job: citation services.
Audit Trail inputs
Persist the filtered payload (the contract), not whatever arrived at the edge:
{
"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."
}Redact secrets before the object hits cold storage.
Decision signals and actions
Minimum fields:
- answer id
- claim text
- source.id + quote hash
- Noul/Score payload
- publish vs strip
Also store usage.input_tokens (vendor meter) and the full probabilities map — argmax-only logs cannot explain a close supports.
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 you cannot explain showing a public citation next to a customer answer from the trace, you are not ready to auto-act. 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
Traces are the eval warehouse. Replay against supports / partial / contradicts on a frozen claim–quote set after criteria or alias changes. 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 | evidence collection |
| Atomic rules | policy checks |
| Act / review / abstain | confidence thresholds |
| Reviewer payload | human handoff |
| What to persist | you are here |
| How it breaks | failure modes |
| Labeled replay | evaluation |
| Shadow → canary | production rollout |
FAQ
Is the HTTP log enough? No. Persist the filtered state, full probabilities, floors, and downstream action as a decision trace.
May I log raw secrets? Redact in code. Jev will not be your DLP layer.
Where is the rest of the Citation pack? Start with Citation human handoff and Citation evaluation. 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.