← The bench

03 · The apparatus

Cross-institutional duplicates

Which sheets in different countries came off the same plant?

Status
In development
Field
Thin — some prior work
Who wants it
Aggregators, repatriation and provenance work, deduplication.

Why it matters

One collection event was split and mailed to a dozen herbaria. Reuniting them builds a global collection-event graph — and for colonial-era collecting, a map of where a place's plants actually ended up.

What it needs

Visual matching plus collector-number matching. The harvest already carries a duplicate-cluster flag on a quarter of records.

State of the art

Record-level clustering exists at the aggregator. Image-level matching is thin.

The working set

63 sheets in the harvest match this head’s starting slice

Open this slice in the catalog →

Next head

Misidentification triage