Directly supported by evidence.
Experiments in AI, archives and human memory
BeginMNEME Memory Lab
Experiments in AI, archives and human memory.
The Memory Lab examines what happens when machines begin interpreting the historical record.
Begin with the vocabulary of evidence, then carry it into four experiments about memory, identity and consent.
LAB 00The threshold
Begin here
How Do You Know That?
A polished caption can make observation, inference and invention sound equally certain. Separate one archival sentence into claims, and name what each rests on.
Audit the caption Round 1 prototype · Approx. 4 minutes · No data collected
NMAAHC 2010.36.11.301 — Ask the ArchiveOpen
What should an intelligent archive refuse to invent?
Question a real historical photograph. The archive distinguishes what is supported, what can be inferred, what remains unknown and what would require invention.
Enter experimentExhibition index
Four experiments. One evidence-first practice.
The MNEME Provenance Layer
A clearer language for uncertain evidence.
The experiments make the questions tangible. The framework is the working method—designed to travel into collections, interpretation, policy and client work.
Reasonable interpretation, but not established.
The archive cannot tell us.
Created rather than recovered.
Toolkit and one-page provenance sheet in development.