Corpus to Frame Logo Corpus to Frame

How it works

A compiler for unstructured text

C2F is not RAG. Not a knowledge graph. Not prompt engineering. It's a structured compilation pipeline that produces governed data products.

The pipeline

1

Grounding

Extract evidence spans from source text

2

Normalization

Types, units, negation, temporal refs

3

Schema Discovery

MECE taxonomy of fields

4

Question Gen

Typed slots from leaf nodes

5

Filling

Extract + version per document

6

Evaluation

Coverage, agreement, evidence rate

Grounding-first

  • No value without evidence. Every extraction is anchored to source text.
  • Uncertainty is explicit. Nulls, uncertain, low-confidence all surface clearly.
  • Failure modes are visible. You see what the system doesn't know.

Evidence map format

{
  "field": "trial_phase",
  "value": "Phase III",
  "confidence": 0.94,
  "evidence": ["...Phase III endpoints met..."],
  "span": [142, 168]
}

What it is not

Not embeddings-only

Inspectable values, not opaque vectors

Not ontology tooling

Ships consumables, not graph schemas

Not RAG

Governed state, not ephemeral answers

Not “LLM extraction”

Structured pipeline with eval, not prompts

See the pipeline in action