research
Proof Structure Carries a Signal of AI Assistance
ProofTrace maps immediate support relationships and finds signatures that survive rewording better than text detectors.
Summary
ProofTrace maps immediate support relationships and finds signatures that survive rewording better than text detectors.
The study assembles five cohorts totaling 8,281 mathematics papers, including historical work, disclosures of substantive AI use, generated manuscripts and matched problem pairs. ProofTrace represents each proof as a graph of immediate support and extracts features of mathematical organization. AI-generated cohorts relied on fewer external results, more intermediate conclusions and different graph connectivity; disclosed papers occupied intermediate positions that shifted over time. In a separate detector, the structural features remained stable under AI rewording while text-based detectors weakened. Incomplete disclosure and cohort construction remain limitations, so the signal is not proof about any individual paper.
Why it matters
ProofTrace maps immediate support relationships and finds signatures that survive rewording better than text detectors.
Limits and context
- Incomplete disclosure and cohort construction remain limitations, so the signal is not proof about any individual paper.
Key claims
ProofTrace maps immediate support relationships and finds signatures that survive rewording better than text detectors.
Qualification: Incomplete disclosure and cohort construction remain limitations, so the signal is not proof about any individual paper.
Evidence: source-2026-11-08-014
Sources
- arXiv preprint 2611.08412, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.