CNC
Concordance
Matching and retrieval
1.0Purpose
What it does
Concordance finds what a record relates to. It runs structured and semantic retrieval across normalised records, where every ranking carries the reasons for it.
A match without a reason cannot be reviewed, so the reasons are part of the result, not an explanation generated afterwards.
2.0Input
What it accepts
- Checked records
- Records that have passed through Conduit and Assay, with their check history.
- Queries
- Structured queries against record fields and semantic queries against record content, singly or combined.
3.0Output
What it emits
- Ranked results
- Candidate matches in ranked order, each carrying the evidence that produced its position.
4.0Config
The configuration surface
Configuration belongs to the client. It encodes what your specialists already know, and it is versioned like code.
- Match definitions
- What counts as a candidate match for each record type.
- Ranking configuration
- The weights and rules behind the order, versioned.
5.0Evidence
What it produces as evidence
- Match records
- A versioned record of each retrieval: the query, the configuration version, the results and the reasons.
6.0Acceptance
What it is tested against
Concordance is tested against acceptance criteria agreed in the statement of work: agreed queries return the agreed matches on a defined corpus, and every result carries its reasons. Retrieval quality is measured by Baseline, not asserted.