What was already known
The paper compares constructions with previously published cap-set lower bounds.
What changed and why it matters
Language-model-generated programs combined with systematic evaluation produced mathematical constructions.
The AI contribution
A pretrained language model proposes programs; an evaluator scores constructions in an evolutionary search.
Limitations
These are improved constructions and lower bounds, not a solution determining the maximum size in all dimensions. AIProofWatch has not independently reproduced the experiments.
Verification evidence
Evidence labels show what supports the claim. Importance rates its impact if correct.
Author claim
Claim reported by the authors.
Accessible artifact / proof
Authors’ public code and supporting material; not independently reproduced here.
Peer review
Published in Nature; peer review does not establish infallibility.
Correction and publication history
Historical seed, researched for the initial catalog. Initial alerting disabled.
Read this published revision