AI Science Tracker
EN

Claude agents prove a sharp spinless modular-bootstrap bound

Anthropic · 7 Nov 2026 · physics

Discovery

Anthropic

Claude agents prove a sharp spinless modular-bootstrap bound

Source check: Source checked. Not independent scientific confirmation.

Finding: Claude agents derived a sharp asymptotic optimal-slope bound for the spinless modular bootstrap at large central charge. The proof artifact was checked in Lean and the result was also reviewed by a physicist. This is a formal theoretical result within the stated spinless setting, not an empirical or universal bound for other bootstrap settings.

Technology: Claude research agents with Lean formal verification

Family Claude: profile · models page

Publication: Preprint · Test context: prospective or independent check. Catalog categories, not an evidence grade.

AI contribution
Claude agents developed the modular-bootstrap argument; Lean proof checking verifies the formalized result, with physicist review described by the sources.
Test and result
The paper states a sharp asymptotic bound and supplies a Lean-checked proof; the reported result is in the spinless, large-central-charge setting.
Limitation / still unknown
Formal verification establishes the encoded theorem relative to its formalization and axioms; it does not establish applicability beyond the stated setting.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://hexagonmath.org/2611.00174v1 · https://www.anthropic.com/research/claude-black-hole-physics

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 4/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse physics discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.