New paths through mathematics.

↙ Return to the open questionsBright record 014 · ScienceInspect the source ↓

The human problem

Some combinatorial problems have vast search spaces.

What changed

The constraint: Researchers develop and evaluate candidate constructions.
AI’s role: Generated programs were tested, selected, and iteratively improved.
The observed result: The study found new constructions for the cap set problem and useful packing heuristics.

The human possibility

Researchers gained an additional experimental tool.

Possible implications are separate from measured outcomes.

Keep following the question.

What holds this up

Mathematical discoveries from program search with large language models ↗

Event date: Not separately established
Source publication: 2023-12-14
Capture date: Not retained in the original record
Claim confidence: Unassessed. Separate from maturity; no numeric certainty inferred.
Review provenance: Legacy source check. No named human editorial approval is recorded.
Evidence state: Demonstrated · What this means
Source checked: 2026-09-05Compared with the published record. No independent replication by Bright.
Replication: Not assessed by Bright
Conflicting findings: Not systematically reviewed

The limits are part of the record.

The approach depends on an evaluator; it is not a general proof engine.

What this classification does—and does not—establish

Bright’s classification applies to the result described here. It does not certify a product, recommend a treatment, or predict a future outcome. Source publication and real-world deployment are different milestones. This opening record may not include every later study.

A record that can change

2026-09-05
Added to the source-checked opening collection.

This is Bright’s catalog history, not a complete history of the research. Future corrections and evidence revisions will be recorded here.

What comes next

Apply verifiable search to other suitable problems.

How corrections change the record ↗