Jev glossary
PatternsStructured-data-extraction cascade
SDE cascade
A two-stage extraction cascade: a mini model extracts, a Noul battery verifies, and a confidence gate escalates to a reasoning model.
- Category
- Patterns
- Also known as
- Structured-data-extraction cascade
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 14
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The pipeline runs gpt-5.4-mini for extraction, verifies each field with one battery of Noul questions in a single call, and escalates to gpt-5.5 when the gate reads 0.7 or below. On an internal 100-prompt sweep it sat up-and-left of every single model on the cost/quality chart.
Its cautionary example is a jsonschema-valid but semantically wrong record that passed validation, showing that verification questions catch errors a schema cannot.
Tagspatternsextractioncost
Related terms
Definitions that connect to this one.
GuardrailScreening messages going into or out of an LLM app with hazard Nouls and severity Scores, then thresholding the probabilities.PatternsConfidence gateA threshold on confidence that decides whether code acts, confirms first, or escalates to a person or a bigger model.Answers & ConfidencePre-parsed value extractionRegex finds candidate spans, then Jev picks the requested one so code copies a verbatim value that cannot be invented.PatternsCost/quality frontierPlotting accuracy against cost and time on log scales, where up and to the left is better; cascades are designed to sit there.Evaluation & Training
From the Jev directory
Directory entries that go deeper on this term.
A two-stage extraction cascade: a mini model extracts, a Noul battery verifies each field in one request, and a 0.7 gate escalates to a reasoning model, sitting on the cost/quality frontier.
Jev CookbooksDocs#official#cookbook#extraction
Official
Architectural patterns for System One systems: speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
Jev Practices & PatternsDocs#official#patterns#architecture
Official
Turn markdown into a knowledge graph with an ontology you write and a cutoff you own. A local decision model answers closed yes-or-no questions one at a time, and anything it is unsure about waits for a person instead of entering the graph.
Jev Repos & SDKs#community#github#rust
Community
raphaelmansuy/edgextractTypeScript
raphaelmansuy/edgextractTypeScriptHAL-X AI's 322M non-autoregressive decision model returns calibrated answers in one forward pass of about 10 ms, with native number, excerpt and citation outputs beyond Jev's choice, noul and score types. Apache-2.0, post-trained in 18 languages.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
A walkthrough that pairs Unsiloed document extraction with Jev: extracted medication rows and their citations become Jev's state, one Noul question per row flags implausible or obscured doses, and the results decide which fields need review.
Jev CookbooksPost#community#catalog-import#yibie
Community
9GitHub stars
A training-free algorithm that gets numerical output from any LLM with a Jev-like structured-choice interface by recursively refining a range through a multiway decision tree. Range-normalized MAE is 1.84% versus 5.18% for direct choice, and code is available on GitHub.
Jev Models & ReimplementationsArticle#community#research#arxiv
Community
Bring-AI/jev-numericPython
Bring-AI/jev-numericPython8 more matching entries in the full directory.
From the Jev AI model community
Posts from builders shipping with Jev right now.