SCOPE
A Mathematical Sky Survey
A systematic search through the open questions between mathematics’ landmarks.
SCOPE develops and deploys AI research methods to explore mathematics at two scales: broad survey work and sustained deep-field investigation.
A research map,
not a publication stream.
SCOPE surveys the mathematical landscape systematically rather than competing for attention one result at a time.
Most findings are intended to remain quiet public records, becoming visible primarily when they are relevant to a researcher exploring the corresponding region of mathematics.
Two ways of looking.
Research architectures are evaluated through experiments and review. Phase II explores literature-led research workflows, refining their design through observed results.
SCOPE Deep,
evolving.
SCOPE Deep’s evolution programme is underway, exploring research methods for longer and deeper investigations. Evaluation focuses on correctness, mathematical value, and inference cost.
- 01Test
Run candidate architectures against the same problems and bounded resources.
- 02Audit
Review claims independently, including failed and incomplete research trajectories.
- 03Evolve
Carry forward the structures that improve correctness, coverage, and inference cost.
SCOPE explores.
Resultary keeps the record.
SCOPE findings are archived with their claims, provenance, and actual review status. Phase II same-model review are explicitly distinguished from independent verification; Resultary provides a discovery interface for the public record.
Search SCOPE records on Resultary